INDEX

Explanations

references to the "G" suite and its various components or features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

lion

-0.16

HQ

-0.15

'gc

-0.15

airie

-0.15

Uvs

-0.15

ãģ£ãģ±

-0.14

ÏģÎ¯Î¿Ïħ

-0.14

Esp

-0.14

gay

-0.14

POSITIVE LOGITS

igo

0.19

IGO

0.18

 drive

0.17

Drive

0.17

ruk

0.16

 Drive

0.16

ocz

0.16

igh

0.16

olang

0.16

igan

0.15

Activations Density 0.028%

references to the "G" suite and its various components or features

No Comments

No Known Activations