INDEX

Explanations

references to personal growth and emotional experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

oad

-0.18

agon

-0.15

ame

-0.14

è¾º

-0.13

 holes

-0.13

LS

-0.13

uddy

-0.13

ulp

-0.13

elt

-0.13

agle

-0.13

POSITIVE LOGITS

 being

0.20

 wanting

0.16

 Various

0.15

being

0.15

 neler

0.15

 certain

0.14

course

0.14

itol

0.14

stitutions

0.14

 having

0.14

Activations Density 0.474%

references to personal growth and emotional experiences

No Comments

No Known Activations