INDEX

Explanations

quantities and measurements related to food, health, and financial data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

vale

-0.15

allet

-0.15

lei

-0.14

.EVT

-0.14

Orm

-0.14

åĿ

-0.14

Deg

-0.14

pedia

-0.14

uess

-0.14

ÃĹ↵↵

-0.14

POSITIVE LOGITS

 perfectly

0.14

 removable

0.14

Ø¶Ø±

0.14

bose

0.13

Rog

0.13

/oauth

0.13

_clone

0.13

 Confeder

0.13

))?

0.13

alley

0.13

Activations Density 0.074%

quantities and measurements related to food, health, and financial data

No Comments

No Known Activations