INDEX

Explanations

phrases associated with health risks and safety assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

olib

-0.17

STATIC

-0.15

bose

-0.15

oodle

-0.15

wig

-0.15

 Inflate

-0.14

onne

-0.14

unal

-0.14

Iterable

-0.14

çħ

-0.14

POSITIVE LOGITS

ãĥ³ãĤ°

0.16

><![

0.15

 Cros

0.15

ritz

0.14

 Membership

0.14

Î»ÎŃ

0.14

asso

0.14

entic

0.14

Lia

0.13

kan

0.13

Activations Density 0.150%

phrases associated with health risks and safety assessments

No Comments

No Known Activations