INDEX

Explanations

concepts related to collaboration and shared objectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 stuff

-0.20

 evidence

-0.17

sti

-0.15

ç£

-0.14

ang

-0.14

cms

-0.14

leck

-0.14

ghi

-0.14

 trouble

-0.14

POSITIVE LOGITS

few

0.16

à¸Ĳà¸²à¸Ļ

0.14

romatic

0.14

apid

0.14

 cancelButtonTitle

0.14

vider

0.14

çĽĺ

0.14

agedList

0.14

 worth

0.14

NCY

0.14

Activations Density 0.455%

concepts related to collaboration and shared objectives

No Comments

No Known Activations