INDEX

Explanations

references to various forms of entertainment or media

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

PLL

-0.15

 Horde

-0.15

(çģ«

-0.15

âĢĮØ¢

-0.15

SYNC

-0.14

ÎµÏģÎ¿

-0.14

rud

-0.14

ording

-0.14

rganization

-0.14

iera

-0.14

POSITIVE LOGITS

gre

0.17

 Fres

0.15

bian

0.15

 relative

0.15

hom

0.15

zent

0.15

0.14

 mean

0.14

issan

0.14

So

0.14

Activations Density 0.188%

references to various forms of entertainment or media

No Comments

No Known Activations