INDEX

Explanations

first-person pronouns indicating personal experiences and thoughts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ibold

-0.15

hir

-0.14

 Checkout

-0.14

rud

-0.14

uld

-0.14

med

-0.14

Å¡t

-0.14

 threshold

-0.14

orelease

-0.13

zin

-0.13

POSITIVE LOGITS

gili

0.17

.ActionListener

0.16

zo

0.15

arth

0.14

\controllers

0.14

atos

0.14

zag

0.14

Ð¼ÐµÑĨÑĮ

0.14

asco

0.13

Activations Density 0.394%

first-person pronouns indicating personal experiences and thoughts

No Comments

No Known Activations