INDEX

Explanations

terms related to consensus and agreement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Ð°Ð»ÐµÐ¶

-0.18

ÐµÐ½Ð·

-0.17

ucher

-0.16

YPE

-0.14

Reviewer

-0.14

 cáº¡nh

-0.14

ekler

-0.14

ALCHEMY

-0.14

Äĩe

-0.14

utow

-0.14

POSITIVE LOGITS

 across

0.21

 among

0.20

 agreed

0.19

/common

0.19

Across

0.19

/shared

0.18

 agreement

0.18

 agree

0.17

 nhau

0.17

 Across

0.17

Activations Density 0.054%

terms related to consensus and agreement

No Comments

No Known Activations