INDEX

Explanations

phrases indicating usability or functionality under certain conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ickerView

-0.16

/owl

-0.16

åĨĨ

-0.15

ODULE

-0.14

 ÄĮer

-0.14

.compiler

-0.14

okit

-0.14

oleon

-0.14

redits

-0.14

aan

-0.14

POSITIVE LOGITS

 barrel

0.17

capt

0.17

 encaps

0.15

 Pilot

0.15

ACES

0.15

vis

0.14

bara

0.14

Me

0.14

lier

0.14

pon

0.14

Activations Density 0.287%

phrases indicating usability or functionality under certain conditions

No Comments

No Known Activations