INDEX

Explanations

terms related to programming and data structuring techniques

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

isz

-0.18

ZD

-0.16

 late

-0.15

alls

-0.14

 mere

-0.14

ingham

-0.14

 Weinstein

-0.14

zl

-0.14

Ov

-0.14

cal

-0.14

POSITIVE LOGITS

 frag

0.15

/commons

0.15

Î¼ÏĨ

0.15

chas

0.15

.fig

0.15

SPA

0.14

.bean

0.14

 Wikispecies

0.14

igu

0.14

 frags

0.14

Activations Density 0.004%

terms related to programming and data structuring techniques

No Comments

No Known Activations