INDEX

Explanations

references to arrests and legal proceedings related to criminal activities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

irse

-0.15

anian

-0.15

.createFrom

-0.15

Ã¡u

-0.14

Responder

-0.14

ello

-0.14

asset

-0.14

ethoven

-0.14

grÃ©

-0.13

 ucwords

-0.13

POSITIVE LOGITS

0.14

 Journal

0.14

\D

0.14

zik

0.14

nite

0.14

anning

0.14

 Firm

0.13

udev

0.13

zm

0.13

 Kathryn

0.13

Activations Density 0.095%

references to arrests and legal proceedings related to criminal activities

No Comments

No Known Activations