INDEX

Explanations

phrases that express subjective evaluations or perceptions of situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ullo

-0.18

anke

-0.15

 undisclosed

-0.15

uner

-0.15

amu

-0.14

iland

-0.14

anki

-0.14

blr

-0.14

iku

-0.14

ugi

-0.14

POSITIVE LOGITS

 innoc

0.31

 straightforward

0.28

 harmless

0.27

 innocent

0.24

 simple

0.24

 obvious

0.23

 normal

0.22

 ordinary

0.21

 Harm

0.20

 initially

0.20

Activations Density 0.103%

phrases that express subjective evaluations or perceptions of situations

No Comments

No Known Activations