INDEX

Explanations

numerical data and statistics related to performance and metrics

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

İ

-0.16

esar

-0.14

 ((((

-0.14

cstdint

-0.14

acus

-0.14

ÑĸÐ´Ñĥ

-0.13

ToRemove

-0.13

 (*((

-0.13

maf

-0.13

ãĤ¤ãĥī

-0.13

POSITIVE LOGITS

onder

0.16

Ing

0.16

alt

0.16

elen

0.15

eline

0.15

erg

0.15

iert

0.15

umnos

0.14

 Schneider

0.14

lassen

0.14

Activations Density 0.145%

numerical data and statistics related to performance and metrics

No Known Activations