INDEX

Explanations

references to recipes and cooking instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

stacle

-0.17

urma

-0.16

zap

-0.15

dÃ¼ÄŁ

-0.15

Bra

-0.15

unge

-0.14

mitters

-0.14

emb

-0.14

ouve

-0.14

rana

-0.14

POSITIVE LOGITS

 steps

0.16

assa

0.16

æŃ¥

0.15

 Lowe

0.15

 ãģ¾

0.15

èĩº

0.15

oyal

0.15

åħ

0.15

 æŃ

0.14

ãģ¾ãģļ

0.14

Activations Density 0.072%

references to recipes and cooking instructions

No Comments

No Known Activations