INDEX

Explanations

references to historical events and time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

otts

-0.16

strup

-0.15

yar

-0.15

 norge

-0.14

 Basket

-0.14

inand

-0.14

.API

-0.14

erged

-0.14

ago

-0.14

icode

-0.13

POSITIVE LOGITS

illy

0.16

avit

0.15

 Iron

0.14

genome

0.14

/post

0.14

ilon

0.14

 Dirty

0.13

onen

0.13

ilder

0.13

Activations Density 0.018%

references to historical events and time periods

No Comments

No Known Activations