INDEX

Explanations

expressions of emotional conflict and personal reflection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

we

-0.18

Personally

-0.15

 they

-0.14

å¤§å®¶

-0.13

åĢĴ

-0.13

 Yours

-0.13

ead

-0.13

ras

-0.13

 abbiamo

-0.13

ivan

-0.13

POSITIVE LOGITS

 deep

0.37

deep

0.30

 Deep

0.29

Deep

0.26

_deep

0.25

 maybe

0.20

 derin

0.20

 deepest

0.19

æ·±

0.19

 Ð³Ð»ÑĥÐ±

0.19

Activations Density 0.446%

expressions of emotional conflict and personal reflection

No Comments

No Known Activations