INDEX

Explanations

references to attendance and participation in meetings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

intree

-0.16

atham

-0.16

Ð¾Ð»ÐµÐ²Ð°

-0.15

.fhir

-0.15

ohen

-0.15

/cgi

-0.14

veau

-0.14

borg

-0.14

ierz

-0.14

oller

-0.14

POSITIVE LOGITS

 attendance

0.32

 Attendance

0.29

attendance

0.27

Attendance

0.25

 presence

0.23

 whereabouts

0.23

 attend

0.20

 attending

0.20

 Presence

0.19

 attended

0.19

Activations Density 0.060%

references to attendance and participation in meetings

No Comments

No Known Activations