INDEX

Explanations

references to APIs and their interactions within code contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

pike

-0.16

ij

-0.15

tu

-0.15

uo

-0.15

ix

-0.15

inations

-0.15

bum

-0.14

vron

-0.14

eya

-0.14

 procur

-0.14

POSITIVE LOGITS

vero

0.15

RG

0.15

yte

0.14

Ã³b

0.14

earch

0.14

 sobie

0.14

çħ§

0.14

illisecond

0.13

itm

0.13

undy

0.13

Activations Density 0.010%

references to APIs and their interactions within code contexts

No Comments

No Known Activations