INDEX

Explanations

negative emotions and descriptions related to difficult or distressing situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

//{{

-0.15

à¤Ĥà¤¶

-0.15

ÃŃcul

-0.14

 Madness

-0.14

Ð°ÑĤÐµÐ³Ð¾ÑĢ

-0.14

rq

-0.14

Ald

-0.14

zzo

-0.13

POSITIVE LOGITS

lest

0.28

omas

0.20

 truth

0.20

dest

0.19

omic

0.19

omik

0.19

 truths

0.19

fully

0.18

 Truth

0.17

 consequences

0.17

Activations Density 0.087%

negative emotions and descriptions related to difficult or distressing situations

No Comments

No Known Activations