INDEX

Explanations

references to political claims and governance issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

kee

-0.16

LEE

-0.15

à¥Ģà¤¬

-0.15

.gs

-0.14

ewe

-0.14

Atlas

-0.14

Ø±Ø§ÙĤ

-0.14

liÅ¡

-0.13

lee

-0.13

rah

-0.13

POSITIVE LOGITS

 traditional

0.19

 Traditional

0.19

ind

0.19

 Paramount

0.17

 stake

0.17

 Stake

0.17

 paramount

0.16

traditional

0.16

Traditional

0.16

akov

0.16

Activations Density 0.060%

references to political claims and governance issues

No Comments

No Known Activations