INDEX

Explanations

references to seasons of a series or show

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 Jacqu

-0.15

Å¡k

-0.15

etary

-0.15

 Leah

-0.15

erdem

-0.14

ustos

-0.14

-Jan

-0.14

ga

-0.14

isz

-0.14

urope

-0.13

POSITIVE LOGITS

0.71

åįģä¸Ģ

0.53

 eleven

0.52

Û±Û±

0.47

 Eleven

0.46

Nov

0.45

 November

0.44

Ele

0.40

ele

0.40

XI

0.39

Activations Density 0.049%

references to seasons of a series or show

No Comments

No Known Activations