INDEX

Explanations

phrases related to safety and regulatory compliance in medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ãĤ¡

-0.15

Ø±Ø¨Ùĩ

-0.14

 Resistance

-0.14

ĩĮ

-0.14

Enlarge

-0.14

Ð»Ð°Ð±

-0.14

<center

-0.14

ynes

-0.14

 scandal

-0.14

 succeeding

-0.13

POSITIVE LOGITS

Yesterday

0.18

 yesterday

0.17

 Yesterday

0.16

appropriate

0.16

 Ð²Ñĩ

0.15

 saddened

0.15

 tonight

0.15

 review

0.14

ãģĶãģĸ

0.14

our

0.14

Activations Density 0.370%

phrases related to safety and regulatory compliance in medical contexts

No Comments

No Known Activations