INDEX

Explanations

citation elements or numerical references commonly found in academic or scholarly texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

bia

-0.17

ania

-0.15

å¤§åħ¨

-0.15

 culture

-0.15

Obs

-0.15

ÑĤÐ¸Ð¼

-0.14

 wagon

-0.14

AndWait

-0.14

 Charg

-0.14

hya

-0.14

POSITIVE LOGITS

assin

0.15

gettext

0.15

ÙĪÛĮØ³

0.14

iable

0.14

à¹ģà¸ģ

0.14

bcm

0.14

ILINE

0.14

-images

0.14

UNC

0.13

_JS

0.13

Activations Density 0.021%

citation elements or numerical references commonly found in academic or scholarly texts

No Comments

No Known Activations