INDEX

Explanations

references to digital or audio media consumption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

@js

-0.15

amide

-0.14

ogrÃ¡f

-0.14

quine

-0.14

utz

-0.13

masÄ±nÄ±

-0.13

 Ø£ÙĦÙģ

-0.13

teÅŁ

-0.13

modulo

-0.12

 Replies

-0.12

POSITIVE LOGITS

 audi

0.51

 audio

0.47

 Audio

0.44

 Audi

0.44

 narr

0.42

audi

0.42

 audible

0.42

 narration

0.41

Aud

0.40

 AUDIO

0.40

Activations Density 0.042%

references to digital or audio media consumption

No Comments

No Known Activations