INDEX

Explanations

instances of silence and stillness in conversations or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ÏĬ

-0.15

æĺĵ

-0.15

CollectionView

-0.14

MBED

-0.14

ernen

-0.13

à¸Ļà¸Ń

-0.13

.inflate

-0.13

itu

-0.13

Reject

-0.13

 decimals

-0.13

POSITIVE LOGITS

 silence

0.91

 Silence

0.78

 silent

0.73

 Silent

0.66

silent

0.62

 silenced

0.58

Sil

0.57

sil

0.57

sil

0.55

 quiet

0.50

Activations Density 0.263%

instances of silence and stillness in conversations or situations

No Comments

No Known Activations