INDEX

Explanations

quantities related to weight measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

com

-0.15

abra

-0.14

veau

-0.14

com

-0.14

ÏĮÏĤ

-0.13

eks

-0.13

 archae

-0.13

undy

-0.13

 wÅĤ

-0.13

POSITIVE LOGITS

mage

0.18

IFE

0.17

etter

0.16

ife

0.15

asa

0.15

Disposition

0.15

nage

0.15

_FRE

0.14

oftware

0.14

filer

0.14

Activations Density 0.009%

quantities related to weight measurements

No Comments

No Known Activations