INDEX

Explanations

references to food

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

AYOUT

-0.17

-0.16

wort

-0.16

tems

-0.15

ILLE

-0.15

dge

-0.15

azo

-0.15

inos

-0.14

/ref

-0.14

ors

-0.13

POSITIVE LOGITS

braco

0.16

ongyang

0.16

.bridge

0.15

igner

0.15

 Wings

0.15

zcze

0.15

agas

0.15

vise

0.14

ardu

0.14

ight

0.14

Activations Density 0.024%

references to food

No Comments

No Known Activations