INDEX

Explanations

technical terms and industry-specific jargon related to programming and system analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ëĿ¼ëıĦ

-0.16

omit

-0.15

otic

-0.14

 trÃ¹ng

-0.14

odont

-0.14

iston

-0.14

MLS

-0.14

Ø§ÙģÙĤ

-0.14

INF

-0.13

mlin

-0.13

POSITIVE LOGITS

edBy

0.17

éĹ

0.17

 simplex

0.16

phies

0.15

 ones

0.15

iator

0.14

ãĤĤãģ®

0.14

lash

0.14

 times

0.13

 affair

0.13

Activations Density 0.366%

technical terms and industry-specific jargon related to programming and system analysis

No Comments

No Known Activations