INDEX

Explanations

symbols and syntax used in programming or markup languages

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

Not in Any Lists

No Comments

Negative Logits

apur

-0.17

sock

-0.14

uji

-0.14

-no

-0.13

etimes

-0.13

oeff

-0.13

zar

-0.13

ucci

-0.13

urette

-0.13

´

-0.13

POSITIVE LOGITS

works

0.15

 Ð´Ð°Ð»

0.14

alist

0.14

ITO

0.14

 Integr

0.14

psilon

0.14

:Register

0.14

_completion

0.13

sty

0.13

roach

0.13

Activations Density 0.002%

symbols and syntax used in programming or markup languages

No Comments

No Known Activations