INDEX

Explanations

mathematical expressions and notation related to variables, functions, and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ells

-0.15

ãĥ³ãĥĦ

-0.15

Pir

-0.15

cxx

-0.14

Kub

-0.14

iere

-0.14

xCF

-0.14

abis

-0.14

oba

-0.13

undan

-0.13

POSITIVE LOGITS

heimer

0.15

werk

0.14

(s

0.14

 Hawth

0.14

Î¯Î¶

0.13

ylon

0.13

oreach

0.13

ÅĻÃŃm

0.13

 Ballard

0.13

ÅĻ

0.13

Activations Density 0.448%

mathematical expressions and notation related to variables, functions, and equations

No Comments

No Known Activations