INDEX

Explanations

various string manipulation and pattern matching elements within code

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

sten

-0.15

readcr

-0.14

inx

-0.14

.Transform

-0.14

alia

-0.14

insula

-0.14

cko

-0.14

rani

-0.14

okus

-0.14

uko

-0.13

POSITIVE LOGITS

nton

0.16

å²³

0.16

ardy

0.16

LabelText

0.16

ä¾Ľ

0.15

à¸ķ

0.14

ve

0.14

éĽ

0.14

walls

0.14

Ñı

0.14

Activations Density 0.038%

various string manipulation and pattern matching elements within code

No Comments

No Known Activations