INDEX

Explanations

occurrences of technical terminologies and references in specialized fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Pump

-0.15

 pumping

-0.15

omik

-0.15

ulumi

-0.15

Ø°Ø±

-0.15

ONGL

-0.15

.colorbar

-0.15

éĴŁ

-0.14

erot

-0.14

efined

-0.14

POSITIVE LOGITS

acula

0.18

à¥ľ

0.15

urb

0.15

 Ø®Ø§Øµ

0.14

Ø§ÛĮÙĩ

0.14

anes

0.14

 ëłĪìĿ´

0.14

_SW

0.14

vell

0.14

lamaya

0.14

Activations Density 0.034%

occurrences of technical terminologies and references in specialized fields

No Comments

No Known Activations