INDEX

Explanations

references to tasks or notes regarding improvements, fixes, or to-do items in code

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

our

-0.15

mean

-0.15

bu

-0.15

 Mean

-0.14

 mean

-0.14

 Gent

-0.14

Ãºi

-0.14

ire

-0.14

DJ

-0.14

bos

-0.13

POSITIVE LOGITS

Ø¡

0.15

ystack

0.15

ĶåĽŀ

0.15

DDS

0.14

.TODO

0.14

Nation

0.14

InputBorder

0.14

icÃŃ

0.14

 creampie

0.14

Activations Density 0.005%

references to tasks or notes regarding improvements, fixes, or to-do items in code

No Comments

No Known Activations