INDEX

Explanations

descriptors related to expertise and professional qualifications

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

geist

-0.16

agy

-0.15

HN

-0.15

å·»

-0.14

quire

-0.14

anian

-0.14

olle

-0.14

çĵ

-0.14

Train

-0.13

erli

-0.13

POSITIVE LOGITS

 enough

0.25

 professionals

0.22

/lic

0.21

 pros

0.18

 Enough

0.18

 hands

0.18

 negot

0.18

urance

0.17

eye

0.17

 professional

0.17

Activations Density 0.071%

descriptors related to expertise and professional qualifications

No Comments

No Known Activations