INDEX

Explanations

references to government positions and official titles

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

arde

-0.16

Jah

-0.14

ologne

-0.14

yst

-0.14

ÙĨØ¹

-0.14

ãĥ³ãĥĹ

-0.13

ental

-0.13

ardy

-0.13

baj

-0.13

itur

-0.13

POSITIVE LOGITS

 Raphael

0.15

ãģ£

0.14

 Gros

0.14

'gc

0.14

metro

0.14

azz

0.14

ÑĢÐ°Ð¿

0.14

ezier

0.13

angle

0.13

Activations Density 0.064%

references to government positions and official titles

No Comments

No Known Activations