INDEX

Explanations

terms related to inflammation and cellular mechanisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

orris

-0.18

.LayoutStyle

-0.15

 Canter

-0.14

dream

-0.14

orida

-0.14

omor

-0.14

oux

-0.14

reur

-0.14

unta

-0.14

ÑĥÐ½Ðº

-0.14

POSITIVE LOGITS

 mast

0.26

 neut

0.25

 prote

0.22

eos

0.21

 released

0.21

 gran

0.20

/release

0.20

 infl

0.19

 inflammatory

0.19

 activation

0.19

Activations Density 0.013%

terms related to inflammation and cellular mechanisms

No Comments

No Known Activations