INDEX

Explanations

terms related to scientific and medical regulations, specifically around treatments and their classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

-0.16

-0.15

ÑģÑĤÐ¸Ñĩ

-0.14

Ð»Ð¸Ðº

-0.14

/includes

-0.14

-sizing

-0.14

-made

-0.14

uz

-0.14

arga

-0.14

-0.13

POSITIVE LOGITS

ighbor

0.17

naire

0.17

-re

0.15

-ex

0.14

 bound

0.14

æķı

0.14

-ab

0.14

 sensitive

0.14

 ØªØ¹Ø¯

0.14

ãģıãģł

0.14

Activations Density 0.110%

terms related to scientific and medical regulations, specifically around treatments and their classifications

No Comments

No Known Activations