INDEX

Explanations

references to online interactions and user engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

iset

-0.15

urga

-0.15

hx

-0.15

seau

-0.15

iu

-0.14

bor

-0.14

iÃ³

-0.14

Cyr

-0.14

imbus

-0.14

pron

-0.14

POSITIVE LOGITS

uce

0.17

 ì§Ī

0.16

sic

0.15

 Opport

0.15

Sic

0.15

FOUNDATION

0.14

NEY

0.14

æ¹¾

0.13

::.

0.13

ErrorHandler

0.13

Activations Density 0.008%

references to online interactions and user engagement

No Comments

No Known Activations