INDEX

Explanations

phrases indicating the creation and organization of resources or lists

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

rej

-0.19

Fab

-0.15

 Wade

-0.15

isson

-0.15

 cont

-0.15

Äįka

-0.15

 Cabr

-0.15

rick

-0.14

oon

-0.14

POSITIVE LOGITS

ains

0.16

embed

0.15

AINS

0.15

inish

0.15

umes

0.15

abi

0.14

PLATFORM

0.14

azu

0.14

icha

0.14

vf

0.14

Activations Density 0.232%

phrases indicating the creation and organization of resources or lists

No Comments

No Known Activations