INDEX

Explanations

negations and assertions related to existence and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 nuclear

-0.14

íĮĲ

-0.14

ifar

-0.14

/browse

-0.13

upport

-0.13

quot

-0.13

ushima

-0.13

Ð²Ð¾Ð´

-0.13

 away

-0.13

rea

-0.13

POSITIVE LOGITS

neau

0.20

iage

0.16

 Slov

0.15

ada

0.15

utter

0.14

union

0.14

ycz

0.14

endir

0.14

Ð²Ð°Ð´

0.14

oice

0.14

Activations Density 1.089%

negations and assertions related to existence and actions

No Comments

No Known Activations