INDEX

Explanations

mathematical notation, specifically related to checks and probabilistic expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ð°ÑĢÑĮ

-0.16

wright

-0.15

Ð´Ð°ÑĤ

-0.15

stime

-0.15

Nom

-0.14

ãĥ¼ãĤ¯

-0.14

 Chung

-0.13

ault

-0.13

_macros

-0.13

weed

-0.13

POSITIVE LOGITS

uÅŁ

0.15

extras

0.15

 ende

0.14

Extras

0.14

onda

0.14

Toolkit

0.14

 åı¸

0.14

azer

0.14

 Territories

0.14

 Roller

0.13

Activations Density 0.138%

mathematical notation, specifically related to checks and probabilistic expressions

No Comments

No Known Activations