INDEX

Explanations

Twitter handles or mentions

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

Not in Any Lists

No Comments

Negative Logits

ffen

-0.18

ulet

-0.17

okit

-0.17

forme

-0.15

kir

-0.15

enha

-0.15

shr

-0.14

 Meta

-0.14

ettel

-0.14

isphere

-0.14

POSITIVE LOGITS

Sco

0.17

RTC

0.16

 fluid

0.14

 gravid

0.14

æ´

0.13

 monet

0.13

eÄį

0.13

atto

0.13

Activations Density 0.002%

Twitter handles or mentions

No Comments

No Known Activations