INDEX

Explanations

information related to voice acting and the people involved in animated productions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 tuner

-0.15

oller

-0.15

beck

-0.15

abit

-0.15

amientos

-0.14

Ł³

-0.14

çľī

-0.14

 ãĥ¬ãĥĩãĤ£ãĥ¼ãĤ¹

-0.14

CISION

-0.14

zeÅĦ

-0.14

POSITIVE LOGITS

 voice

0.46

vo

0.40

 voices

0.39

 Voice

0.38

voice

0.36

 voiced

0.34

vo

0.33

voz

0.31

Voice

0.31

VO

0.31

Activations Density 0.026%

information related to voice acting and the people involved in animated productions

No Comments

No Known Activations