INDEX

Explanations

LaTeX commands and document structure indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 ãĥĽ

-0.15

arbon

-0.14

 flux

-0.14

 Parker

-0.14

Liked

-0.14

\param

-0.14

igel

-0.14

Routine

-0.13

 Celtic

-0.13

POSITIVE LOGITS

use

0.23

Require

0.21

use

0.19

pagen

0.17

geometry

0.17

Expl

0.17

Pass

0.16

ilton

0.16

rag

0.16

document

0.15

Activations Density 0.012%

LaTeX commands and document structure indicators

No Comments

No Known Activations