INDEX

Explanations

code snippets, specifically focusing on variable types and definitions

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

 atol

-0.14

ãĥ¼ãĥĭ

-0.14

 concrete

-0.14

ored

-0.14

urus

-0.14

bur

-0.14

athed

-0.14

INED

-0.14

ather

-0.13

 hooked

-0.13

POSITIVE LOGITS

format

0.15

ichert

0.15

icha

0.15

 Pork

0.14

_lowercase

0.13

adaki

0.13

Ð¾Ð»Ð¾ÑĤ

0.13

éª¨

0.13

estro

0.13

rix

0.13

Activations Density 0.223%

code snippets, specifically focusing on variable types and definitions

No Comments

No Known Activations