INDEX

Explanations

references to government actions and discussions

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

 shit

-0.16

Ø§ÙĩÙħ

-0.16

aleigh

-0.15

shit

-0.14

[attr

-0.14

ÑĮÑİÑĤ

-0.14

eli

-0.14

ali

-0.14

 Definitely

-0.13

POSITIVE LOGITS

inde

0.20

 indeed

0.20

uh

0.18

 Indeed

0.17

 ought

0.17

 sorts

0.17

âĢİ

0.17

Fol

0.16

Indeed

0.16

sort

0.16

Activations Density 0.305%

references to government actions and discussions

No Comments

No Known Activations