INDEX

Explanations

references to organizational structures and networks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

lit

-0.16

Lit

-0.16

ertz

-0.15

shot

-0.15

 opak

-0.15

 consc

-0.15

ose

-0.14

ause

-0.14

_interrupt

-0.14

pak

-0.14

POSITIVE LOGITS

 local

0.24

local

0.23

 Local

0.22

 regional

0.21

 locales

0.21

ToLocal

0.21

 Regional

0.20

/local

0.20

Local

0.20

 lokal

0.19

Activations Density 0.203%

references to organizational structures and networks

No Comments

No Known Activations