INDEX

Explanations

names of individuals and their associated titles 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 @ 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

iac

-0.16

lette

-0.15

AAD

-0.14

ethoven

-0.14

ErrorException

-0.14

mie

-0.13

chia

-0.13

è²©

-0.13

spd

-0.13

.Undef

-0.13

POSITIVE LOGITS

imiter

0.17

 Towers

0.15

 consort

0.14

ycz

0.14

plements

0.13

 Duis

0.13

ADA

0.13

imiters

0.13

 Thá»ĭ

0.13

.shiro

0.13

Activations Density 0.569%

names of individuals and their associated titles or roles

No Comments

No Known Activations

names of individuals and their associated titles or roles

No Comments

No Known Activations