INDEX

Explanations

phrases indicating negation or lack of experience

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

hop

-0.15

uchen

-0.15

 instead

-0.14

erap

-0.14

æĿ¥è¯´

-0.14

chn

-0.13

ogg

-0.13

inand

-0.13

chk

-0.13

 intermitt

-0.13

POSITIVE LOGITS

 necessarily

0.28

 anymore

0.22

 particularly

0.21

 ever

0.20

 really

0.20

particularly

0.19

 bother

0.17

 unless

0.17

really

0.17

 quite

0.16

Activations Density 0.158%

phrases indicating negation or lack of experience

No Comments

No Known Activations