INDEX

Explanations

programming syntax, particularly in relation to properties and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

_FUN

-0.16

uffy

-0.15

ilder

-0.15

 Blitz

-0.14

Fin

-0.14

 speech

-0.14

anko

-0.14

èįĴ

-0.13

ander

-0.13

lÃ©d

-0.13

POSITIVE LOGITS

 nipple

0.15

adians

0.15

semicolon

0.15

neau

0.15

 Bare

0.15

 bites

0.14

 nipples

0.14

urt

0.14

URRENT

0.14

æĻ´

0.14

Activations Density 0.261%

programming syntax, particularly in relation to properties and parameters

No Comments

No Known Activations