INDEX

Explanations

geographical names and references related to specific locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Hammer

-0.17

ex

-0.16

 spot

-0.15

felt

-0.15

min

-0.15

raj

-0.15

iedo

-0.15

 Hell

-0.15

-0.14

Sus

-0.14

POSITIVE LOGITS

patrick

0.17

Î¶ÏĮ

0.15

.ua

0.15

swick

0.14

ë¦½

0.14

éĻĲ

0.14

ardÄ±m

0.14

ÏĥÏĥ

0.14

'&&

0.14

 Drum

0.14

Activations Density 0.024%

geographical names and references related to specific locations

No Comments

No Known Activations