INDEX

Explanations

expressions related to media or radio shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 televis

-0.19

TVs

-0.18

TV

-0.18

 ÑĤÐµÐ»

-0.18

ãĥĨãĥ¬ãĥĵ

-0.18

TV

-0.18

 television

-0.17

Tv

-0.17

éĽ»è¦ĸ

-0.17

_TV

-0.17

POSITIVE LOGITS

 listeners

0.24

 listener

0.23

Listeners

0.21

 listen

0.18

 radio

0.18

 listened

0.17

listener

0.17

listeners

0.17

 Radio

0.17

 Podcast

0.17

Activations Density 0.042%

expressions related to media or radio shows

No Comments

No Known Activations