INDEX

Explanations

statistics related to numbers and percentages in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

oms

-0.15

hy

-0.14

anzi

-0.14

ÐµÑģÑĤÐ²

-0.14

.Dynamic

-0.13

è¦

-0.13

ÑģÐ¸ÑĤ

-0.13

hole

-0.13

aspect

-0.13

stry

-0.13

POSITIVE LOGITS

 persons

0.18

 cÃ¡i

0.17

 fewer

0.16

 ÑĪÑĤÑĥ

0.16

ê°ľ

0.16

 total

0.15

 souls

0.15

sessions

0.15

 count

0.14

iki

0.14

Activations Density 0.091%

statistics related to numbers and percentages in various contexts

No Comments

No Known Activations