INDEX

Explanations

references to organized religious structures and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

affle

-0.16

ivy

-0.16

dbh

-0.14

acker

-0.14

Hao

-0.14

çĺ

-0.14

adle

-0.13

 neutral

-0.13

à¸¯

-0.13

ield

-0.13

POSITIVE LOGITS

 part

0.47

 among

0.35

 amongst

0.32

part

0.31

among

0.30

 alongside

0.29

 Ø¬Ø²Ø¡

0.29

 along

0.28

 participate

0.27

 participating

0.27

Activations Density 0.262%

references to organized religious structures and events

No Comments

No Known Activations