INDEX

Explanations

lines of code or text labels in the context of user interface development

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

vido

-0.15

umba

-0.15

 Cher

-0.15

wap

-0.15

ombine

-0.14

isiyle

-0.14

åİ

-0.14

gad

-0.14

czy

-0.14

ationToken

-0.14

POSITIVE LOGITS

utherland

0.19

orm

0.16

ur

0.15

LEAR

0.14

ora

0.14

esa

0.14

orm

0.14

 Zaman

0.14

ï»¿using

0.14

aty

0.13

Activations Density 0.001%

lines of code or text labels in the context of user interface development

No Comments

No Known Activations