INDEX

Explanations

references to acknowledgments and bibliographic citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

Ã¸y

-0.17

arendra

-0.16

ahat

-0.16

terra

-0.15

aket

-0.14

 èĩªåĬ¨çĶŁæĪĲ

-0.14

ê³¡

-0.14

anda

-0.14

aga

-0.14

 éĵģ

-0.14

POSITIVE LOGITS

 Waters

0.16

emons

0.14

STALL

0.14

athed

0.14

 summers

0.14

 Serena

0.13

æ·

0.13

venida

0.13

eeper

0.13

Cav

0.13

Activations Density 0.026%

references to acknowledgments and bibliographic citations

No Comments

No Known Activations