INDEX

Explanations

instances of quotation marks, indicating the presence of direct speech or citations

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

-0.22

the

-0.21

fragistics

-0.18

those

-0.18

the

-0.18

aN

-0.18

Intialized

-0.18

 that

-0.17

an

-0.17

POSITIVE LOGITS

most

0.25

ultimate

0.23

golden

0.22

usual

0.21

Golden

0.21

raison

0.21

 Golden

0.20

 greatest

0.20

 most

0.20

 golden

0.20

Activations Density 0.073%

instances of quotation marks, indicating the presence of direct speech or citations

No Comments

No Known Activations