INDEX

Explanations

code blocks and property definitions in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

tok

-0.15

xffffffff

-0.15

éĶ

-0.14

ICODE

-0.14

 Ãĸl

-0.14

 Mills

-0.14

agini

-0.14

 Graham

-0.14

/repos

-0.13

 Pearce

-0.13

POSITIVE LOGITS

antar

0.17

dez

0.15

.getCurrentUser

0.15

Vz

0.15

ToProps

0.14

vell

0.14

hin

0.14

ounge

0.13

ucz

0.13

angan

0.13

Activations Density 0.036%

code blocks and property definitions in programming contexts

No Comments

No Known Activations