INDEX

Explanations

references to programming-related objects and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

oding

-0.15

amura

-0.15

anke

-0.15

etri

-0.14

auge

-0.14

tq

-0.14

elter

-0.14

Jun

-0.14

ertoire

-0.14

opsis

-0.14

POSITIVE LOGITS

utton

0.16

ourn

0.14

 direct

0.14

ubar

0.14

å¸¯

0.14

ennie

0.14

Fon

0.14

utor

0.14

 interests

0.13

Activations Density 0.003%

references to programming-related objects and structures

No Comments

No Known Activations