INDEX

Explanations

references to historical or biblical figures and their actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

omy

-0.16

anga

-0.15

åºĦ

-0.15

 Township

-0.14

ursal

-0.14

ordable

-0.14

opi

-0.14

è²´

-0.14

erli

-0.13

raq

-0.13

POSITIVE LOGITS

 Damascus

0.26

 persec

0.19

 Saul

0.19

 Paul

0.17

Paul

0.16

Rab

0.16

icens

0.16

 Felix

0.15

GIT

0.15

 wings

0.15

Activations Density 0.019%

references to historical or biblical figures and their actions

No Comments

No Known Activations