INDEX

Explanations

phrases emphasizing availability or options in various contexts

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

ve

-0.17

veau

-0.16

sss

-0.16

tring

-0.16

shit

-0.15

son

-0.15

ÄŁa

-0.15

 seul

-0.15

leans

-0.14

POSITIVE LOGITS

curity

0.20

quence

0.20

cond

0.16

è²¬

0.15

è´£

0.15

quential

0.15

 beiden

0.14

Ã³m

0.14

 themselves

0.14

 meisten

0.14

Activations Density 0.119%

phrases emphasizing availability or options in various contexts

No Comments

No Known Activations