INDEX

Explanations

terms related to inflammation and inflammatory conditions

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

beh

-0.16

åĢĳ

-0.16

å¤§åĪ©

-0.15

aylor

-0.15

inals

-0.14

geh

-0.14

vise

-0.14

eler

-0.14

INY

-0.14

iny

-0.14

POSITIVE LOGITS

ary

0.22

ations

0.22

ateur

0.20

ationToken

0.19

stery

0.18

atory

0.18

arity

0.17

atted

0.17

idable

0.16

atories

0.15

Activations Density 0.010%

terms related to inflammation and inflammatory conditions

No Comments

No Known Activations