INDEX

Explanations

code syntax elements related to function and object definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

nad

-0.17

ruc

-0.15

AssignableFrom

-0.15

Disallow

-0.15

EDITOR

-0.14

oblin

-0.14

onso

-0.14

YSTEM

-0.14

ĶåĽŀ

-0.14

istra

-0.13

POSITIVE LOGITS

0.17

prd

0.14

Kop

0.14

 Rubin

0.14

weak

0.14

ungan

0.13

Î³ÎºÏĮ

0.13

åĢī

0.13

chio

0.13

_COMPAT

0.13

Activations Density 0.005%

code syntax elements related to function and object definitions

No Comments

No Known Activations