INDEX

Explanations

words and phrases indicating specialized skills or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

rette

-0.20

Ã©rÃ©

-0.17

-0.16

reten

-0.16

bare

-0.15

piar

-0.15

ÏĢÎŃ

-0.15

ØªØ±ÛĮ

-0.15

 Bare

-0.15

POSITIVE LOGITS

lu

0.15

è¯

0.14

hoff

0.14

rab

0.14

åĳ

0.14

ells

0.14

inde

0.14

è«¸

0.14

ç

0.14

ung

0.14

Activations Density 0.058%

words and phrases indicating specialized skills or roles

No Comments

No Known Activations