INDEX

Explanations

expressions related to behavioral expectations and norms

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

elow

-0.15

Ã¡ly

-0.15

utow

-0.15

illos

-0.15

eteor

-0.14

 iken

-0.14

 Grove

-0.14

bette

-0.14

vio

-0.14

adr

-0.14

POSITIVE LOGITS

oq

0.16

nid

0.16

 tern

0.15

Ð·ÑĮ

0.14

inely

0.14

son

0.14

cour

0.14

AIN

0.14

omic

0.14

Activations Density 0.506%

expressions related to behavioral expectations and norms

No Comments

No Known Activations