INDEX

Explanations

descriptors of personal attributes and qualities relevant to job candidates

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

uzey

-0.18

mime

-0.16

è¡

-0.16

oyo

-0.15

vail

-0.15

 diligently

-0.15

á»ĭp

-0.14

angelo

-0.14

 Dans

-0.14

 Ð¼ÐµÑĤÐ°Ð»Ð»Ð¸

-0.14

POSITIVE LOGITS

 detail

0.33

 results

0.30

results

0.27

 goal

0.27

 outcome

0.26

 result

0.25

 Detail

0.25

Results

0.24

 Results

0.24

detail

0.24

Activations Density 0.083%

descriptors of personal attributes and qualities relevant to job candidates

No Comments

No Known Activations