INDEX

Explanations

references to specific individuals or terms related to "Kabuki" and "Kubrick."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

/documentation

-0.17

ophon

-0.16

ollah

-0.16

UBLE

-0.15

icable

-0.14

Ãłnh

-0.14

uated

-0.14

ÎºÏĮ

-0.14

olly

-0.14

ICO

-0.14

POSITIVE LOGITS

upaten

0.18

ocha

0.17

itzer

0.14

 Enumeration

0.14

inka

0.14

 tang

0.14

ker

0.13

utom

0.13

ried

0.13

Gen

0.13

Activations Density 0.008%

references to specific individuals or terms related to "Kabuki" and "Kubrick."

No Comments

No Known Activations