INDEX

Explanations

a specific legal or procedural term related to voting processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.15

osy

-0.15

vise

-0.14

orum

-0.14

 pued

-0.14

aeda

-0.14

 Deng

-0.14

outil

-0.13

wand

-0.13

anden

-0.13

POSITIVE LOGITS

nish

0.15

ocha

0.14

 seriousness

0.14

uzzi

0.14

 Ying

0.13

 caps

0.13

ØªÙĪÙĨ

0.13

 Watkins

0.13

éłĥ

0.13

oday

0.13

Activations Density 0.000%

a specific legal or procedural term related to voting processes

No Comments

No Known Activations