INDEX

Explanations

terms related to voice acting and animation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

beck

-0.16

ogl

-0.15

cura

-0.15

Ł³

-0.14

abit

-0.14

ategory

-0.14

phet

-0.14

agal

-0.14

-horizontal

-0.14

oller

-0.13

POSITIVE LOGITS

 voice

0.54

 Voice

0.48

 voices

0.46

vo

0.45

voice

0.44

Voice

0.39

VO

0.38

 voiced

0.38

 Voices

0.36

vo

0.35

Activations Density 0.031%

terms related to voice acting and animation

No Comments

No Known Activations