INDEX

Explanations

specific version numbers and software release information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

croft

-0.16

agrid

-0.16

 åĨĨ

-0.15

ndon

-0.15

avic

-0.15

aben

-0.14

zia

-0.14

aly

-0.14

ãģ«ãĤĪ

-0.14

ÄŁ

-0.13

POSITIVE LOGITS

ereum

0.15

ì§ľ

0.15

-era

0.15

 ÙħÛĮÙĦØ§Ø¯ÛĮ

0.14

âĢ³

0.14

-transitional

0.14

forme

0.14

osp

0.14

lvl

0.14

icie

0.13

Activations Density 0.040%

specific version numbers and software release information

No Comments

No Known Activations