INDEX

Explanations

references to historical events or figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

oyer

-0.17

abo

-0.16

eldig

-0.15

 firma

-0.14

ipa

-0.14

Bone

-0.14

éĢŁ

-0.14

 Atkins

-0.14

 meld

-0.14

orny

-0.14

POSITIVE LOGITS

 fetisch

0.22

 Orient

0.21

 Erotische

0.17

bens

0.16

 Anders

0.16

Bed

0.15

Geh

0.15

eworld

0.15

abcdefghijkl

0.15

apper

0.15

Activations Density 0.102%

references to historical events or figures

No Comments

No Known Activations