INDEX

Explanations

references to various aspects of subjects or topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ucc

-0.16

Ã¨ve

-0.15

dy

-0.15

Lay

-0.14

ÑĢÐ°Ð´

-0.14

ska

-0.14

vyk

-0.13

 Stad

-0.13

lay

-0.13

ÙĪØ±Ø©

-0.13

POSITIVE LOGITS

ãĥ³ãĥĸ

0.16

pects

0.15

alan

0.15

illis

0.15

iles

0.15

onom

0.14

illes

0.14

 Throne

0.14

ãģŃ

0.13

ê·¼

0.13

Activations Density 0.015%

references to various aspects of subjects or topics

No Comments

No Known Activations