INDEX

Explanations

words and phrases related to trust and betrayal 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 @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

prak

-0.15

desk

-0.15

unan

-0.15

à¸³

-0.15

iaz

-0.14

ivable

-0.14

ãĥ¼ãĥĦ

-0.14

ToFront

-0.14

fleet

-0.14

ativity

-0.14

POSITIVE LOGITS

 trust

1.05

 Trust

0.90

trust

0.89

Trust

0.87

 trusts

0.81

 trusted

0.72

 trusting

0.72

trusted

0.66

 trustworthy

0.60

 confidence

0.54

Activations Density 0.230%

words and phrases related to trust and betrayal in relationships

No Comments

No Known Activations