INDEX

Explanations

programming-related keywords and structures in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

vore

-0.16

Ĥæķ°

-0.16

RequestId

-0.15

abela

-0.15

ÏĦÎ¯Î±

-0.15

otto

-0.15

ierte

-0.15

vro

-0.14

isiert

-0.14

berapa

-0.14

POSITIVE LOGITS

Cub

0.15

å¯Ĵ

0.15

Sed

0.15

.scalablytyped

0.15

_easy

0.15

achel

0.14

Cod

0.14

 populate

0.14

 Leonardo

0.14

Activations Density 0.005%

programming-related keywords and structures in code

No Comments

No Known Activations