INDEX

Explanations

information related to medical expertise and safety assurances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

oldt

-0.14

 cheaper

-0.14

 supposedly

-0.14

 theorists

-0.13

 Argument

-0.13

 disasters

-0.13

 theoretically

-0.12

Argument

-0.12

Ø´Ø±

-0.12

 nich

-0.12

POSITIVE LOGITS

our

0.26

 unfortunately

0.23

 regret

0.23

 unfortunate

0.22

 ourselves

0.22

we

0.22

 saddened

0.20

 respectful

0.19

 ours

0.18

 respectfully

0.18

Activations Density 0.338%

information related to medical expertise and safety assurances

No Comments

No Known Activations