INDEX

Explanations

terms related to occupation or occupancy

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.16

-0.15

iz

-0.15

ight

-0.15

ict

-0.15

ux

-0.14

atches

-0.14

iac

-0.14

bor

-0.14

ine

-0.14

POSITIVE LOGITS

 occup

0.18

IED

0.17

adel

0.17

ationally

0.17

åĲĪãĤıãģĽ

0.16

ational

0.15

ATIONS

0.15

 Occup

0.15

 occupation

0.15

ancy

0.15

Activations Density 0.016%

terms related to occupation or occupancy

No Comments

No Known Activations