INDEX

Explanations

references to antiques and antique-related items or stores

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ê·¼

-0.15

ase

-0.14

usc

-0.14

hn

-0.14

.scalablytyped

-0.14

ÏĢÎ¿ÏĦÎµ

-0.14

asurement

-0.13

æŀľ

-0.13

empre

-0.13

apse

-0.13

POSITIVE LOGITS

anela

0.16

ÐµÑĢÐ¿

0.15

<typeof

0.15

teri

0.15

TES

0.14

ì¹

0.14

à¸²à¸ģà¸£

0.14

GPC

0.14

dar

0.14

adal

0.14

Activations Density 0.005%

references to antiques and antique-related items or stores

No Comments

No Known Activations