INDEX

Explanations

concepts and terminology related to health, finance, and data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Jungle

-0.15

 exit

-0.15

 Hook

-0.15

odi

-0.15

ungle

-0.14

.mdl

-0.14

>{!!

-0.14

upe

-0.14

REC

-0.14

idth

-0.14

POSITIVE LOGITS

alim

0.17

zas

0.17

intage

0.17

razier

0.16

ZX

0.16

éļª

0.16

ÙĦÙħÙĩ

0.14

Ã¤l

0.13

Ø§ÙĬÙĦ

0.13

_squared

0.13

Activations Density 0.051%

concepts and terminology related to health, finance, and data analysis

No Comments

No Known Activations