INDEX

Explanations

references to political processes and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

opher

-0.15

cliffe

-0.15

ystore

-0.15

èĽĽ

-0.15

.getColumnIndex

-0.15

labs

-0.15

 consequat

-0.14

enson

-0.14

kop

-0.14

 ÑģÐ»ÑĥÑħ

-0.14

POSITIVE LOGITS

Aug

0.17

OK

0.16

OK

0.16

 Engel

0.15

etter

0.15

 puck

0.14

 Bett

0.14

 dozens

0.14

 Frank

0.14

 Lake

0.14

Activations Density 0.008%

references to political processes and their implications

No Comments

No Known Activations