INDEX

Explanations

words that express actions or conditions involving strong physical and emotional states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ey

-0.22

eeee

-0.22

eyer

-0.22

asure

-0.19

eee

-0.19

utenant

-0.17

BERS

-0.17

conut

-0.17

asures

-0.17

efa

-0.17

POSITIVE LOGITS

esign

0.41

orf

0.33

ragon

0.32

own

0.31

iamond

0.30

iction

0.29

irect

0.28

owns

0.28

uct

0.28

ed

0.28

Activations Density 0.108%

words that express actions or conditions involving strong physical and emotional states

No Comments

No Known Activations