INDEX

Explanations

references to medical professionals and their specializations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

.sf

-0.16

ÙĨØ¯Ú¯ÛĮ

-0.15

 Ð²ÐµÐ´ÑĮ

-0.14

elles

-0.14

boro

-0.14

cura

-0.14

olle

-0.13

loom

-0.13

tery

-0.13

 hiring

-0.13

POSITIVE LOGITS

 playback

0.22

 Additional

0.21

Pad

0.21

 Playback

0.20

Playback

0.18

 exponent

0.18

 bureauc

0.18

 litter

0.17

IAS

0.17

CMD

0.17

Activations Density 0.217%

references to medical professionals and their specializations

No Comments

No Known Activations