INDEX

Explanations

information related to dates, errors, and specifications in technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

-0.14

aza

-0.13

enza

-0.13

osite

-0.13

 Lowe

-0.13

GRADE

-0.13

bon

-0.13

Ð¾ÑģÐº

-0.13

chio

-0.13

loth

-0.13

POSITIVE LOGITS

Lua

0.18

wik

0.17

/doc

0.16

_align

0.16

oader

0.16

zell

0.15

 rowspan

0.15

idd

0.15

 }}↵

0.15

aks

0.15

Activations Density 0.033%

information related to dates, errors, and specifications in technical contexts

No Comments

No Known Activations