INDEX

Explanations

phrases that signal a type of categorization or classification

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

anga

-0.15

indre

-0.15

nection

-0.14

 Remote

-0.14

ojenÃŃ

-0.14

urdy

-0.14

Ð¾ÑģÑĮ

-0.13

Ð°Ð´Ñĥ

-0.13

actable

-0.13

 èĩ

-0.13

POSITIVE LOGITS

neau

0.16

acre

0.15

 PageSize

0.15

0.14

abee

0.14

ãģ¡

0.14

 Lambert

0.13

 ------------------------------------------------------------

0.13

assen

0.13

place

0.13

Activations Density 0.005%

phrases that signal a type of categorization or classification

No Comments

No Known Activations