INDEX

Explanations

references to historical figures and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

idar

-0.15

ueur

-0.15

 Andres

-0.15

Hab

-0.14

apur

-0.14

ammer

-0.14

 parsley

-0.14

 Ezra

-0.13

Prefs

-0.13

anonymous

-0.13

POSITIVE LOGITS

 count

0.20

 Counts

0.19

 princ

0.18

 counts

0.18

 Bourbon

0.18

Counts

0.17

 Count

0.17

/count

0.17

 Prince

0.17

semb

0.15

Activations Density 0.056%

references to historical figures and their relationships

No Comments

No Known Activations