INDEX

Explanations

references to specific films, particularly titles and elements related to horror and supernatural themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

oste

-0.15

strip

-0.15

 Medieval

-0.15

 sneak

-0.15

em

-0.15

BarItem

-0.14

Sne

-0.14

 holog

-0.14

BV

-0.13

anca

-0.13

POSITIVE LOGITS

Nec

0.20

åĦĢ

0.20

Yog

0.19

 Love

0.18

ãĥĥãĥĹ

0.17

Ĵ

0.17

kul

0.17

 elder

0.17

Love

0.17

 ActionTypes

0.17

Activations Density 0.028%

references to specific films, particularly titles and elements related to horror and supernatural themes

No Comments

No Known Activations