INDEX

Explanations

specific measurements and quantities related to dietary components and health

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

è²¨

-0.14

 Krank

-0.14

ÙĪØ±Ø¯

-0.14

agos

-0.13

Gro

-0.13

acia

-0.13

 GeÃ§

-0.13

/xhtml

-0.13

UDGE

-0.13

hin

-0.13

POSITIVE LOGITS

 gram

0.49

 grams

0.48

grams

0.45

gram

0.45

 gramm

0.45

mg

0.42

 Gram

0.42

mg

0.40

gm

0.39

Activations Density 0.054%

specific measurements and quantities related to dietary components and health

No Comments

No Known Activations