INDEX

Explanations

instances of contact information, specifically email addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

tring

-0.17

avax

-0.16

 Ashe

-0.15

reich

-0.14

 Sexe

-0.14

izens

-0.14

pii

-0.14

/static

-0.14

lea

-0.14

abei

-0.14

POSITIVE LOGITS

ertino

0.18

ozy

0.15

interop

0.14

@show

0.14

="[

0.13

 embar

0.13

isch

0.13

Å¡e

0.13

 chooser

0.13

wn

0.13

Activations Density 0.010%

instances of contact information, specifically email addresses

No Comments

No Known Activations