INDEX

Explanations

occurrences of the word "of" and variations in language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

les

-0.17

iliz

-0.16

ainer

-0.16

wis

-0.16

.qml

-0.15

_UNLOCK

-0.15

ellig

-0.14

sync

-0.14

otr

-0.14

enza

-0.14

POSITIVE LOGITS

Che

0.23

Che

0.21

che

0.20

_che

0.20

che

0.19

CHE

0.17

-che

0.17

axon

0.16

AKE

0.16

CHE

0.16

Activations Density 0.027%

occurrences of the word "of" and variations in language

No Comments

No Known Activations