INDEX

Explanations

phrases related to medical care and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Ø§Ø¬

-0.16

 neither

-0.16

olo

-0.15

Nin

-0.15

-0.14

egas

-0.14

icker

-0.14

FW

-0.14

phon

-0.14

POSITIVE LOGITS

 apart

0.36

 Apart

0.35

Apart

0.34

 majority

0.27

 Majority

0.27

 aside

0.26

 Aside

0.25

Aside

0.22

aside

0.22

 Prior

0.16

Activations Density 0.039%

phrases related to medical care and services

No Comments

No Known Activations