INDEX

Explanations

terms related to clinical settings or medical professionals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

azes

-0.17

ussed

-0.17

rous

-0.16

HD

-0.15

oom

-0.14

eous

-0.14

ieu

-0.14

POSITIVE LOGITS

ician

0.31

ching

0.30

ched

0.27

cher

0.25

ches

0.24

icians

0.23

icient

0.21

ically

0.20

chers

0.19

ch

0.19

Activations Density 0.003%

terms related to clinical settings or medical professionals

No Comments

No Known Activations