INDEX

Explanations

mathematical symbols and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

es

-0.15

ohan

-0.15

gre

-0.14

Markup

-0.14

ikat

-0.14

 Nass

-0.13

erva

-0.13

avers

-0.13

à¹Īà¸ķ

-0.13

(TestCase

-0.13

POSITIVE LOGITS

=:

0.18

=Value

0.17

0.16

modx

0.15

+(

0.14

 Wolver

0.14

htdocs

0.14

ekim

0.14

anel

0.14

endl

0.13

Activations Density 0.420%

mathematical symbols and notations

No Comments

No Known Activations