INDEX

Explanations

instances of emotional expressions and social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

/Peak

-0.16

ÎºÎ¬

-0.15

egas

-0.14

ACHI

-0.14

 humiliation

-0.14

 åĭ

-0.14

incare

-0.14

.LoadScene

-0.14

defer

-0.13

urovision

-0.13

POSITIVE LOGITS

 complain

0.62

 complaint

0.61

 complaining

0.58

 complaints

0.57

 complains

0.52

 Complaint

0.51

 complained

0.50

 lament

0.40

mo

0.38

 grip

0.36

Activations Density 0.440%

instances of emotional expressions and social interactions

No Comments

No Known Activations