INDEX

Explanations

references to data breaches and compromised user information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Quang

-0.16

ipo

-0.15

Î¶Î±

-0.15

andex

-0.15

inkel

-0.15

rael

-0.14

acher

-0.14

aman

-0.14

 Î£Ïį

-0.14

áº§u

-0.13

POSITIVE LOGITS

vaz

0.16

uckle

0.15

Bundle

0.15

.opensource

0.15

 bundled

0.15

 bundles

0.14

Î½ÎµÎ¹

0.14

 bundle

0.14

UNDLE

0.14

MOTE

0.14

Activations Density 0.241%

references to data breaches and compromised user information

No Comments

No Known Activations