INDEX

Explanations

terms related to business and organizational processes

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

oya

-0.16

oner

-0.15

aload

-0.15

ÃŃch

-0.15

Pun

-0.15

iga

-0.15

 employee

-0.15

Å¡ak

-0.15

ardu

-0.14

igo

-0.14

POSITIVE LOGITS

-unit

0.19

Unit

0.18

 Critical

0.18

 critical

0.17

 intelligence

0.17

 logic

0.16

 Unit

0.16

critical

0.16

 unit

0.16

Activations Density 0.020%

terms related to business and organizational processes

No Comments

No Known Activations