INDEX

Explanations

references to individuals and their participation in events or meetings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ouse

-0.14

lasses

-0.14

ç´ł

-0.14

 Dive

-0.13

ading

-0.13

()){

-0.13

.startActivity

-0.13

enses

-0.13

Helmet

-0.13

landing

-0.13

POSITIVE LOGITS

 presence

0.66

presence

0.58

 Presence

0.57

 attendance

0.55

 present

0.52

Presence

0.52

attendance

0.46

 Attendance

0.43

_presence

0.43

 presente

0.43

Activations Density 0.288%

references to individuals and their participation in events or meetings

No Comments

No Known Activations