INDEX

Explanations

instances of significant quantities or states of being

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

inders

-0.16

errupted

-0.15

 Sever

-0.14

reed

-0.14

 mand

-0.14

rij

-0.14

 Mand

-0.14

dit

-0.14

Ir

-0.14

POSITIVE LOGITS

uzu

0.17

ecta

0.16

ABCDEFGHIJKLMNOP

0.16

ABCDEFGHI

0.15

Ĭ

0.15

aggi

0.14

åī²

0.14

.openg

0.14

hood

0.14

LOPT

0.14

Activations Density 0.091%

instances of significant quantities or states of being

No Comments

No Known Activations