INDEX

Explanations

mentions of specific products or brands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ingles

-0.16

obe

-0.15

 Hiring

-0.14

nez

-0.14

axed

-0.14

strpos

-0.13

ãĥ¼ãĥĹ

-0.13

 Supply

-0.13

 OMAP

-0.13

reesome

-0.13

POSITIVE LOGITS

 replacement

0.20

 replace

0.19

 replacing

0.19

 replaced

0.19

 owned

0.18

 ownership

0.18

 upgrade

0.18

 Ownership

0.18

 gift

0.17

Replacing

0.17

Activations Density 0.140%

mentions of specific products or brands

No Comments

No Known Activations