INDEX

Explanations

references to coding and programming structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

asco

-0.17

ouse

-0.16

 Guinea

-0.15

antino

-0.14

reet

-0.14

 close

-0.14

 Lang

-0.14

oor

-0.14

 Sang

-0.13

Ph

-0.13

POSITIVE LOGITS

-Semit

0.17

nech

0.15

 æ¹

0.15

icana

0.15

 sáº¯c

0.15

 Tomas

0.15

ÑĥÑĩÐ°

0.15

/tutorial

0.14

 gáº¥p

0.14

ometown

0.14

Activations Density 0.023%

references to coding and programming structures

No Comments

No Known Activations