INDEX

Explanations

references to "sunshine" and related terms

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

enu

-0.16

arest

-0.16

ities

-0.15

aggio

-0.15

 Hayward

-0.14

ts

-0.14

ondon

-0.14

agy

-0.14

eller

-0.14

Åĳ

-0.14

POSITIVE LOGITS

fat

0.18

vat

0.17

Ð½Ð°ÑĩÐµ

0.15

rames

0.15

braco

0.15

 ê·¸ë¦¬

0.15

EventData

0.15

trap

0.14

etak

0.14

createClass

0.14

Activations Density 0.003%

references to "sunshine" and related terms

No Comments

No Known Activations