INDEX

Explanations

acknowledgments and expressions of indulgence

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

atts

-0.17

fleet

-0.16

Lens

-0.15

eus

-0.15

.scalablytyped

-0.15

 meiden

-0.15

RelativeTo

-0.14

osph

-0.14

ESIS

-0.14

Ø´Ø¯

-0.14

POSITIVE LOGITS

ging

0.46

ged

0.45

ges

0.42

GING

0.33

gments

0.32

gement

0.32

gem

0.31

ger

0.30

gment

0.30

gements

0.29

Activations Density 0.019%

acknowledgments and expressions of indulgence

No Comments

No Known Activations