INDEX

Explanations

elements related to employment and job stability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

wan

-0.15

inic

-0.14

ãĥ¼ãĤ¿

-0.14

ippi

-0.13

achuset

-0.13

 einmal

-0.12

odont

-0.12

 Î±Î½Î¬

-0.12

 dormant

-0.12

amon

-0.12

POSITIVE LOGITS

 stay

0.65

 stays

0.62

 Stay

0.59

 stayed

0.59

stay

0.58

Stay

0.57

 retained

0.57

 staying

0.56

 retention

0.55

 retain

0.54

Activations Density 0.534%

elements related to employment and job stability

No Comments

No Known Activations