INDEX

Explanations

mentions of film or entertainment franchises and their characteristics

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

enden

-0.15

gren

-0.15

-elect

-0.14

heets

-0.14

ths

-0.14

err

-0.13

reeze

-0.13

oten

-0.13

POSITIVE LOGITS

illo

0.16

dil

0.15

adÃŃ

0.14

uttle

0.14

Ð¾ÑģÑĥÐ´

0.14

Ð¡Ðł

0.14

æĮ

0.14

audi

0.14

 ActionTypes

0.13

par

0.13

Activations Density 0.040%

mentions of film or entertainment franchises and their characteristics

No Comments

No Known Activations