INDEX

Explanations

phrases that express expectations or assessments regarding social interactions and participation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

YPE

-0.20

isations

-0.15

bury

-0.15

ansson

-0.14

SCII

-0.14

ibur

-0.14

ÑĢÐ°Ð±

-0.14

 setError

-0.14

 Buccane

-0.14

 Prev

-0.14

POSITIVE LOGITS

 whenever

0.23

 Whenever

0.18

Whenever

0.18

 future

0.18

OAD

0.17

anj

0.15

Spo

0.15

à¥įà¤ľ

0.14

asa

0.14

 anymore

0.14

Activations Density 0.296%

phrases that express expectations or assessments regarding social interactions and participation

No Comments

No Known Activations