INDEX

Explanations

phrases related to narration and contributions in literary works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Ãºng

-0.16

 wrote

-0.15

 indeb

-0.14

çª

-0.14

-horizontal

-0.14

 composed

-0.14

icana

-0.14

ylland

-0.14

 mess

-0.14

MTV

-0.14

POSITIVE LOGITS

 audio

0.25

 audi

0.24

 podcast

0.22

Pod

0.21

audio

0.21

 Audio

0.20

(audio

0.20

pod

0.20

 podcasts

0.20

pod

0.19

Activations Density 0.106%

phrases related to narration and contributions in literary works

No Comments

No Known Activations