INDEX

Explanations

mentions of archival institutions and their contributions

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

arium

-0.15

 perd

-0.15

uly

-0.14

iei

-0.14

inha

-0.14

bout

-0.14

pek

-0.14

Īëĭ¤

-0.13

czy

-0.13

unik

-0.13

POSITIVE LOGITS

abh

0.21

bh

0.21

Eag

0.19

Bh

0.19

 Sonra

0.18

adh

0.18

acht

0.18

dh

0.18

iom

0.17

 cuid

0.17

Activations Density 0.016%

mentions of archival institutions and their contributions

No Comments

No Known Activations

mentions of archival institutions and their contributions

No Comments

No Known Activations