INDEX

Explanations

terms related to prevention and preventative measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ripple

-0.18

lesi

-0.16

baum

-0.16

hover

-0.15

ëŁī

-0.15

agnetic

-0.15

 CreateTable

-0.15

aptors

-0.14

 "-",

-0.14

egov

-0.14

POSITIVE LOGITS

/pre

0.24

/mit

0.20

atives

0.18

 against

0.17

ively

0.16

ubb

0.16

 prob

0.15

ive

0.15

 Against

0.15

Activations Density 0.021%

terms related to prevention and preventative measures

No Comments

No Known Activations