INDEX

Explanations

terms related to transactions or applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Ð½Ð°Ð´Ð»ÐµÐ¶

-0.17

urtles

-0.15

aos

-0.14

tera

-0.13

 inert

-0.13

utra

-0.13

 PropertyChangedEventArgs

-0.13

ansi

-0.13

geme

-0.13

Ð²Ð¾Ð»Ñı

-0.13

POSITIVE LOGITS

0.16

Ãłi

0.16

is

0.16

 involved

0.15

 were

0.15

obot

0.15

 contains

0.15

fos

0.15

 itself

0.15

å°ļ

0.15

Activations Density 0.122%

terms related to transactions or applications

No Comments

No Known Activations