INDEX

Explanations

phrases related to accountability and justifications in relationships

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

assert

-0.15

ucht

-0.14

ittest

-0.14

arf

-0.14

izzo

-0.14

rejected

-0.13

elfth

-0.13

 assert

-0.13

Mahon

-0.13

 Jensen

-0.13

POSITIVE LOGITS

 forgiving

0.28

 forgiven

0.24

 allowances

0.24

 forgiveness

0.24

 forg

0.24

 forgive

0.22

 fair

0.21

 excuses

0.21

fair

0.21

 unfair

0.21

Activations Density 0.140%

phrases related to accountability and justifications in relationships

No Comments

No Known Activations