INDEX

Explanations

terms related to financial metrics and performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ean

-0.16

-0.14

Ã¢u

-0.14

_usec

-0.14

Ĥ

-0.14

jist

-0.14

èĤ¡

-0.14

iente

-0.14

azen

-0.14

 STRICT

-0.13

POSITIVE LOGITS

er

0.25

 domestic

0.24

ly

0.23

/net

0.23

esse

0.23

 Domestic

0.22

ing

0.21

ed

0.21

ingham

0.20

ular

0.19

Activations Density 0.012%

terms related to financial metrics and performance

No Comments

No Known Activations