INDEX

Explanations

terms related to regulations, rights, and liabilities concerning hazardous items, employee conditions, and medical contexts

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

imen

-0.19

pector

-0.19

anko

-0.16

 Serif

-0.15

strict

-0.15

untos

-0.14

pton

-0.14

uzu

-0.14

enu

-0.14

uml

-0.14

POSITIVE LOGITS

 Rouge

0.15

etta

0.15

yles

0.15

ãģ¨ãģ¯

0.15

ÃŃna

0.14

 Chore

0.14

ISCO

0.14

 Blackburn

0.14

uf

0.14

 incent

0.14

Activations Density 0.391%

terms related to regulations, rights, and liabilities concerning hazardous items, employee conditions, and medical contexts

No Comments

No Known Activations