INDEX

Explanations

references to novel ideas or products

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

olecule

-0.15

 Canter

-0.15

antaged

-0.14

ungeon

-0.14

Kab

-0.14

?url

-0.14

ibox

-0.14

rowable

-0.14

 Snape

-0.14

POSITIVE LOGITS

ieg

0.17

irt

0.14

STRU

0.14

ÑĢÐ¾Ð¹

0.14

ÄĽst

0.14

ech

0.14

Î»Î»Î·

0.14

ewise

0.13

meric

0.13

ãĥ¼ãĥĩ

0.13

Activations Density 0.040%

references to novel ideas or products

No Comments

No Known Activations