INDEX

Explanations

references to specific locations and community development projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

illis

-0.17

agher

-0.16

ubern

-0.15

licer

-0.15

andi

-0.15

âĹİ

-0.15

IGO

-0.14

ewan

-0.14

_PTR

-0.14

 Trab

-0.14

POSITIVE LOGITS

oz

0.17

oen

0.15

isan

0.15

zym

0.15

owi

0.15

0.14

ingleton

0.14

 unfit

0.14

ould

0.14

etics

0.14

Activations Density 0.151%

references to specific locations and community development projects

No Comments

No Known Activations