INDEX

Explanations

proper nouns relating to people, places, and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Ð¸Ð½Ð¸

-0.16

_idxs

-0.15

inn

-0.15

-0.14

↵

-0.14

ois

-0.14

aval

-0.14

 Beaut

-0.14

truck

-0.14

POSITIVE LOGITS

Î¼ÏĢÎ¿

0.15

odnÃŃ

0.15

.appspot

0.15

zby

0.15

imb

0.15

ENCIES

0.15

productive

0.14

hire

0.14

isper

0.14

jvu

0.14

Activations Density 0.112%

proper nouns relating to people, places, and organizations

No Comments

No Known Activations