INDEX

Explanations

references to dates or years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 Pascal

-0.18

Lal

-0.15

umd

-0.14

 telesc

-0.14

 Dank

-0.14

twig

-0.14

adam

-0.14

om

-0.13

um

-0.13

 Lage

-0.13

POSITIVE LOGITS

kaar

0.19

utow

0.16

aq

0.16

 chatte

0.16

 pokoj

0.15

.scalajs

0.15

uese

0.15

atz

0.14

edium

0.14

ÑģÐ¾ÑĢ

0.14

Activations Density 0.034%

references to dates or years

No Comments

No Known Activations