INDEX

Explanations

references to individuals involved in legal or political scandals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

cken

-0.15

 double

-0.15

icion

-0.15

utherland

-0.15

 Triple

-0.15

ug

-0.14

zac

-0.14

 Opportunities

-0.13

nd

-0.13

ÙĪÙĦÙĬÙĪ

-0.13

POSITIVE LOGITS

quan

0.17

 advoc

0.15

çĻº

0.14

0.13

vae

0.13

gee

0.13

áº»

0.13

lut

0.13

ÑĢÐ°Ð¶

0.13

heb

0.13

Activations Density 0.000%

references to individuals involved in legal or political scandals

No Comments

No Known Activations