INDEX

Explanations

prominent pop culture references and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

dney

-0.17

rame

-0.17

empo

-0.16

åļ

-0.16

egen

-0.16

ŀ

-0.16

YRO

-0.15

apat

-0.15

.trade

-0.14

Ð¿ÑĢÐ°

-0.14

POSITIVE LOGITS

itech

0.17

action

0.16

 accompany

0.15

.lon

0.14

 Sund

0.14

ARAM

0.14

 action

0.14

bon

0.13

 eins

0.13

 Styles

0.13

Activations Density 0.312%

prominent pop culture references and events

No Comments

No Known Activations