INDEX

Explanations

phrases that suggest the act of avoiding or evading something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

eters

-0.15

 volta

-0.15

 Exiting

-0.15

FieldValue

-0.14

alf

-0.14

?key

-0.14

/Dk

-0.14

vui

-0.14

 Levin

-0.13

aybe

-0.13

POSITIVE LOGITS

ance

0.18

lingen

0.16

/mit

0.16

rette

0.15

obus

0.15

Avoid

0.15

 Avoid

0.15

 saturation

0.14

avoid

0.14

Activations Density 0.013%

phrases that suggest the act of avoiding or evading something

No Comments

No Known Activations