INDEX

Explanations

programming-related keywords and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

_lite

-0.15

amped

-0.15

aker

-0.14

DED

-0.14

ictory

-0.14

-Sah

-0.14

CLK

-0.14

å¸ģ

-0.14

fgang

-0.14

opus

-0.14

POSITIVE LOGITS

ÐµÑĢÐ°Ð»ÑĮ

0.16

Odd

0.16

Ð¼Ð°Ð·

0.16

 Unknown

0.15

fak

0.15

ollipop

0.14

zy

0.14

mod

0.14

afc

0.14

Activations Density 0.004%

programming-related keywords and identifiers

No Comments

No Known Activations