INDEX

Explanations

code-related annotations and directives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

rix

-0.17

Ð°Ñı

-0.16

ay

-0.15

idal

-0.14

Ì£

-0.14

 éļ

-0.14

use

-0.14

Browsable

-0.13

asons

-0.13

erson

-0.13

POSITIVE LOGITS

ippers

0.17

ghest

0.15

ToSelector

0.15

oldur

0.14

kÃ³w

0.14

quat

0.14

endregion

0.14

 impro

0.14

eyse

0.14

gers

0.14

Activations Density 0.005%

code-related annotations and directives

No Comments

No Known Activations