INDEX

Explanations

references to darkness or dark imagery

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

hog

-0.17

plate

-0.16

ç½

-0.13

fi

-0.13

chor

-0.13

 Plate

-0.13

oucher

-0.13

vinces

-0.13

axy

-0.13

 Plates

-0.13

POSITIVE LOGITS

deposit

0.15

à¸£à¸¡

0.15

amba

0.15

epam

0.14

ElementException

0.14

celand

0.14

alte

0.14

errupt

0.14

Lou

0.13

_ALWAYS

0.13

Activations Density 0.005%

references to darkness or dark imagery

No Comments

No Known Activations