INDEX

Explanations

coding-related keywords and programming syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

erver

-0.15

aclass

-0.14

HY

-0.14

keterangan

-0.14

pl

-0.14

pix

-0.14

Ã¦k

-0.14

odied

-0.14

unm

-0.13

POSITIVE LOGITS

owitz

0.17

 Hubbard

0.16

rÅ¾

0.16

ÙĪÚ©

0.15

 Propel

0.15

LETE

0.15

ìłķë¶Ģ

0.15

 çķĻ

0.14

rico

0.14

 Ú©ÛĮÙĦ

0.14

Activations Density 0.010%

coding-related keywords and programming syntax

No Comments

No Known Activations