INDEX

Explanations

references to investors and investment-related terms

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

pone

-0.16

med

-0.16

 Principle

-0.15

iske

-0.15

ilim

-0.14

umann

-0.14

assa

-0.13

 principle

-0.13

elp

-0.13

outh

-0.13

POSITIVE LOGITS

MBER

0.15

uell

0.14

isia

0.14

plr

0.14

 interest

0.14

uyáº¿n

0.13

 zÃ¡jem

0.13

à¤Ĥà¤ľà¤¨

0.13

uede

0.13

zimmer

0.13

Activations Density 0.009%

references to investors and investment-related terms

No Comments

No Known Activations