INDEX

Explanations

references to academic journals and research methodologies

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

ije

-0.17

ambre

-0.16

ija

-0.14

urette

-0.14

æı

-0.14

ina

-0.13

VD

-0.13

antan

-0.13

entrada

-0.13

 pose

-0.13

POSITIVE LOGITS

ardon

0.16

 KrÃ¡l

0.15

èĳĹ

0.15

rak

0.15

0.14

ERCHANT

0.14

\xaa

0.14

isman

0.14

lisi

0.13

croft

0.13

Activations Density 0.006%

references to academic journals and research methodologies

No Comments

No Known Activations