INDEX

Explanations

code snippets and programming constructs related to parsing and handling strings

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

uluk

-0.15

zeÅĦ

-0.15

addtogroup

-0.15

smarty

-0.14

(~(

-0.14

ocrat

-0.14

ritz

-0.14

Ð¾Ð»ÑĮ

-0.14

iamo

-0.14

otle

-0.14

POSITIVE LOGITS

tol

0.16

ereg

0.16

fen

0.15

gard

0.15

 Manning

0.14

ocol

0.14

boz

0.14

 Evel

0.14

 rÃ¡m

0.14

Activations Density 0.565%

code snippets and programming constructs related to parsing and handling strings

No Known Activations