INDEX

Explanations

locations related to performances and events

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

hic

-0.16

echan

-0.16

Ñĳ

-0.15

 somewhere

-0.15

 mechan

-0.14

itur

-0.14

 åĮº

-0.14

aks

-0.13

asic

-0.13

som

-0.13

POSITIVE LOGITS

 Annex

0.21

 auditor

0.18

 complex

0.17

0.16

á»ĥn

0.16

 annex

0.16

 doors

0.16

 Complex

0.15

 Auditor

0.15

ÏĨÎ±Ïģ

0.15

Activations Density 0.108%

locations related to performances and events

No Comments

No Known Activations