INDEX

Explanations

specific markers or symbols used in textual or categorical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

jem

-0.17

#/

-0.15

inox

-0.15

SCRI

-0.14

åĸ

-0.14

/INFO

-0.14

flo

-0.14

Luo

-0.13

kel

-0.13

tember

-0.13

POSITIVE LOGITS

antu

0.17

å¡

0.15

ovsky

0.14

Ã³t

0.14

/sweetalert

0.14

ublic

0.14

0.13

 Speedway

0.13

akash

0.13

uppe

0.13

Activations Density 0.007%

specific markers or symbols used in textual or categorical data

No Comments

No Known Activations