INDEX

Explanations

references to specific biological categories or classifications

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

ativos

-0.40

nicos

-0.34

izados

-0.32

ivos

-0.31

ificados

-0.30

licos

-0.30

 ceux

-0.29

Ã¡rios

-0.28

undos

-0.28

idos

-0.27

POSITIVE LOGITS

las

0.43

las

0.41

Ã¡ticas

0.40

Las

0.40

Las

0.39

adas

0.38

ativas

0.37

nicas

0.35

 ellas

0.35

icas

0.33

Activations Density 0.067%

references to specific biological categories or classifications

No Comments

No Known Activations