INDEX

Explanations

programming annotations and warnings related to code safety and linting

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

kest

-0.19

bane

-0.16

andal

-0.16

avin

-0.15

èĬĿ

-0.15

ngr

-0.15

 alphabet

-0.15

á»Ļng

-0.15

åĽ½äº§

-0.14

gth

-0.14

POSITIVE LOGITS

riday

0.16

ÙĪÛĮÙĦ

0.16

ridge

0.15

quit

0.14

del

0.14

à¹Ħà¸ĭ

0.14

 CORPOR

0.14

pace

0.14

lund

0.14

mond

0.14

Activations Density 0.010%

programming annotations and warnings related to code safety and linting

No Known Activations