INDEX

Explanations

significant numerical values or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

vron

-0.17

Vault

-0.17

aggi

-0.17

aal

-0.15

 Vault

-0.14

ListItemIcon

-0.14

Ð°ÑĢÑĮ

-0.14

ÎļÎ±

-0.14

reeNode

-0.14

POSITIVE LOGITS

Ìĥ

0.15

 severe

0.15

ÐµÑī

0.14

æ²ĥ

0.14

 opportun

0.13

 Compound

0.13

oth

0.13

Activations Density 0.100%

significant numerical values or statistics

No Comments

No Known Activations