INDEX

Explanations

occurrences of the word "Mass" and its variations, indicating a focus on the term's relevance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

pty

-0.16

eyn

-0.16

 Masks

-0.14

 investigator

-0.14

/manage

-0.14

jÅ¡ÃŃ

-0.14

ty

-0.14

emia

-0.14

 masks

-0.14

unning

-0.14

POSITIVE LOGITS

achusetts

0.36

ively

0.31

iveness

0.29

aging

0.28

achuset

0.27

imo

0.24

ive

0.24

oud

0.24

acre

0.24

ses

0.23

Activations Density 0.022%

occurrences of the word "Mass" and its variations, indicating a focus on the term's relevance in various contexts

No Comments

No Known Activations