INDEX

Explanations

references to external sources or citations

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

doch

-0.17

ennes

-0.16

_RT

-0.15

etes

-0.15

viso

-0.15

gett

-0.14

empo

-0.14

å¥ĳ

-0.14

Dog

-0.14

orb

-0.14

POSITIVE LOGITS

az

0.15

 Bros

0.15

 cref

0.14

Us

0.14

Pri

0.14

vi

0.13

 bosses

0.13

oho

0.13

ATER

0.13

Activations Density 0.022%

references to external sources or citations

No Comments

No Known Activations