INDEX

Explanations

references to blogging and community engagement through personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

è¾°

-0.18

anka

-0.15

å¢ĥ

-0.15

udad

-0.15

oucher

-0.15

ouchers

-0.14

PLE

-0.14

 otherwise

-0.14

otherwise

-0.14

ople

-0.14

POSITIVE LOGITS

uiltin

0.17

Ã©ric

0.16

ĥģ

0.15

Fam

0.15

dings

0.15

UILTIN

0.15

addtogroup

0.14

Éµ

0.14

ennon

0.14

canf

0.14

Activations Density 0.577%

references to blogging and community engagement through personal experiences

No Comments

No Known Activations