INDEX

Explanations

expressions of fear or concern

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

erate

-0.17

eydi

-0.17

roker

-0.15

lage

-0.15

weis

-0.15

lige

-0.15

ize

-0.15

euillez

-0.15

ively

-0.14

POSITIVE LOGITS

 stiff

0.24

 scared

0.18

emas

0.16

 afraid

0.16

nes

0.16

iff

0.16

terr

0.16

 scare

0.15

ness

0.15

 enough

0.14

Activations Density 0.023%

expressions of fear or concern

No Comments

No Known Activations