INDEX

Explanations

introductory phrases indicating the source of information or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

viron

-0.16

.gg

-0.14

 memo

-0.14

Ð°ÑĪ

-0.14

ft

-0.14

ole

-0.14

alis

-0.14

-0.13

ibus

-0.13

 BÃłi

-0.13

POSITIVE LOGITS

 humble

0.17

maj

0.17

covering

0.17

eland

0.16

 covering

0.15

 simple

0.15

å±

0.15

æ¶

0.14

 nutrition

0.14

ENDOR

0.14

Activations Density 0.040%

introductory phrases indicating the source of information or statements

No Comments

No Known Activations