INDEX

Explanations

programming-related structures and functions

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

ensch

-0.17

seau

-0.16

kont

-0.15

kin

-0.15

å§Ĳ

-0.14

orde

-0.14

pte

-0.14

utton

-0.14

ubbo

-0.14

.Apis

-0.14

POSITIVE LOGITS

0.15

Cob

0.15

0.14

ÑĢÑĸÐ´

0.14

 propTypes

0.14

INF

0.14

aint

0.14

PK

0.14

 Oliv

0.13

 Rosenberg

0.13

Activations Density 0.003%

programming-related structures and functions

No Comments

No Known Activations