INDEX

Explanations

references to statistical changes or trends over time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Lens

-0.15

opi

-0.15

esin

-0.14

éłĤ

-0.14

ÏģÏİ

-0.14

ellar

-0.14

sor

-0.13

éĢ£

-0.13

rum

-0.13

Dai

-0.13

POSITIVE LOGITS

quan

0.16

ilet

0.15

 ngÅ©

0.15

ync

0.15

à¥Įà¤°

0.14

.scalablytyped

0.14

åĬĩ

0.14

anner

0.14

.styles

0.14

ole

0.14

Activations Density 0.045%

references to statistical changes or trends over time

No Comments

No Known Activations