INDEX

Explanations

phrases and terms related to significant improvements or changes in quantitative measures or performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 cref

-0.17

ernal

-0.16

andro

-0.14

LLU

-0.14

tow

-0.14

haven

-0.13

éĻ°

-0.13

 Äįek

-0.13

 Katz

-0.13

arty

-0.13

POSITIVE LOGITS

edic

0.17

cities

0.16

oken

0.15

oa

0.14

../../../../

0.14

 Trem

0.14

zf

0.14

 Hugo

0.13

à¥Ģà¤£

0.13

Activations Density 0.122%

phrases and terms related to significant improvements or changes in quantitative measures or performance metrics

No Comments

No Known Activations