INDEX

Explanations

instances of examples and explanations in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ãģĿãģ®ä»ĸ

-0.16

 åħ¶ä»ĸ

-0.16

 others

-0.16

 other

-0.16

ãģĿãģĹãģ¦

-0.14

 also

-0.14

Others

-0.14

 moreover

-0.14

semble

-0.13

RI

-0.13

POSITIVE LOGITS

 ÙħØ«ÙĦØ§

0.19

coni

0.16

inear

0.16

ipur

0.15

 Whereas

0.14

 Ð½Ð°Ð¿ÑĢÐ¸Ð¼ÐµÑĢ

0.14

ikk

0.14

 etwa

0.14

 whereas

0.14

Activations Density 0.201%

instances of examples and explanations in the text

No Comments

No Known Activations