INDEX

Explanations

mentions of audio and audio-related content

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

ma

-0.17

gar

-0.17

erna

-0.17

wn

-0.17

rello

-0.16

å£

-0.16

wide

-0.16

 Ð´ÑĥÐ¼Ð°

-0.15

mal

-0.15

teen

-0.15

POSITIVE LOGITS

visual

0.41

/video

0.27

Visual

0.23

 Visual

0.21

-video

0.20

 visual

0.20

VIS

0.19

Ø¤

0.19

.visual

0.17

/image

0.17

Activations Density 0.011%

mentions of audio and audio-related content

No Comments

No Known Activations