INDEX

Explanations

technical terms and concepts related to law, business, and computation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ault

-0.16

uckets

-0.15

Ú¯ÛĮ

-0.15

rew

-0.15

åĬ±

-0.15

 Duty

-0.14

brig

-0.14

ryption

-0.14

orang

-0.13

ÙĪØ²ÛĮ

-0.13

POSITIVE LOGITS

edis

0.16

_COMPAT

0.15

uhn

0.15

ONGO

0.14

lei

0.14

ç·ł

0.14

 Chronicle

0.14

 Nexus

0.14

_VC

0.13

AINED

0.13

Activations Density 0.011%

technical terms and concepts related to law, business, and computation

No Comments

No Known Activations