INDEX

Explanations

references to various societies and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

av

-0.17

ature

-0.15

rest

-0.14

avior

-0.14

ELS

-0.14

 hann

-0.14

nat

-0.14

arat

-0.14

 feliz

-0.13

å¹ķ

-0.13

POSITIVE LOGITS

igne

0.18

kest

0.16

WindowText

0.16

enci

0.15

okin

0.15

optera

0.14

ë°ķ

0.14

erville

0.14

 dá»¥

0.14

uforia

0.14

Activations Density 0.020%

references to various societies and organizations

No Comments

No Known Activations