INDEX

Explanations

terms related to chemical inhibition and inhibitors in biological contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ibur

-0.15

ifen

-0.14

aggi

-0.14

§

-0.14

itas

-0.13

ä¾

-0.13

URITY

-0.13

ived

-0.13

ature

-0.13

atures

-0.13

POSITIVE LOGITS

åŁºäºİ

0.15

uir

0.15

Ink

0.14

 Fragment

0.14

vement

0.14

anse

0.14

/sdk

0.14

istÃ©

0.14

veis

0.14

deÅŁ

0.14

Activations Density 0.006%

terms related to chemical inhibition and inhibitors in biological contexts

No Comments

No Known Activations