INDEX

Explanations

references to exorcisms, particularly in religious contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

chet

-0.15

oug

-0.15

ãĤ

-0.14

ãĥ¼ãĥ©

-0.14

à¸¡à¸Ļà¸ķà¸£

-0.13

LCS

-0.13

ORMAT

-0.13

.toJSONString

-0.13

ancel

-0.13

ims

-0.13

POSITIVE LOGITS

pap

0.59

 Pope

0.54

Pap

0.51

 pope

0.50

 Ð¿Ð°Ð¿

0.44

 Vatican

0.43

 pont

0.40

 Rome

0.35

 Cardinals

0.34

 Pont

0.33

Activations Density 0.181%

references to exorcisms, particularly in religious contexts

No Comments

No Known Activations