INDEX

Explanations

references to drama and tension in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ackers

-0.18

earing

-0.17

-0.15

isz

-0.15

lds

-0.15

áº«

-0.15

Ð¼ÐµÑĤÑĮ

-0.14

acre

-0.14

laus

-0.14

.AutoScaleMode

-0.14

POSITIVE LOGITS

ulance

0.15

-league

0.15

ith

0.14

fab

0.14

ÏģÏĩ

0.14

 Campos

0.14

 Ruth

0.13

wie

0.13

uate

0.13

urg

0.13

Activations Density 0.046%

references to drama and tension in various contexts

No Comments

No Known Activations