INDEX

Explanations

reference links or citations in the text

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

ÌĤ

-0.15

.tencent

-0.14

EDIA

-0.14

?("

-0.14

orem

-0.14

ansi

-0.14

ilmington

-0.14

reads

-0.14

ÑģÑĮ

-0.14

Éµ

-0.13

POSITIVE LOGITS

zew

0.15

 incom

0.15

yte

0.15

èĲ

0.14

rends

0.14

 Mana

0.14

erm

0.14

Zip

0.14

Ã¤tz

0.14

Activations Density 0.000%

reference links or citations in the text

No Comments

No Known Activations