INDEX

Explanations

events and actions related to significant occurrences or transitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

alarÄ±nda

-0.12

zÃ¡

-0.12

ãģ«ãģĭ

-0.12

#================================================================

-0.12

Ã¤ng

-0.12

#----------------------------------------------------------------

-0.12

ìĩ

-0.11

------+------+

-0.11

ivol

-0.11

dej

-0.11

POSITIVE LOGITS

 from

1.05

from

0.84

 FROM

0.73

 frÃ¥n

0.73

 tá»«

0.72

	from

0.71

 dari

0.69

 From

0.66

_from

0.65

à¸Īà¸²à¸ģ

0.65

Activations Density 0.751%

events and actions related to significant occurrences or transitions

No Comments

No Known Activations