INDEX

Explanations

phrases indicating importance, rankings, or notable characteristics related to various subjects, particularly in medical and architectural contexts

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

elta

-0.15

oker

-0.14

enting

-0.14

 convention

-0.13

 Hart

-0.13

brace

-0.13

/home

-0.13

 Hipp

-0.13

POSITIVE LOGITS

 among

0.21

among

0.20

 amongst

0.19

 Among

0.18

ä¹ĭä¸Ģ

0.18

Among

0.16

inet

0.15

SED

0.15

 ÑģÑĢÐµÐ´Ð¸

0.15

_ER

0.14

Activations Density 0.101%

phrases indicating importance, rankings, or notable characteristics related to various subjects, particularly in medical and architectural contexts

No Comments

No Known Activations