INDEX

Explanations

titles of popular films and shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ople

-0.15

afka

-0.14

<typeof

-0.14

rowable

-0.14

riere

-0.14

ÑĢÐ¾ÑģÑĤÐ¾

-0.13

weets

-0.13

bek

-0.13

enter

-0.13

ycin

-0.13

POSITIVE LOGITS

 Confidential

0.16

 supporting

0.16

 Wars

0.15

amma

0.15

 typealias

0.14

 expend

0.14

ãģĻãģĻ

0.14

ropa

0.14

.GraphicsUnit

0.14

OLON

0.14

Activations Density 0.219%

titles of popular films and shows

No Comments

No Known Activations