INDEX

Explanations

comparative phrases emphasizing additional qualities or quantities

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

ÃŃnÄĽ

-0.15

ark

-0.15

Âį

-0.15

ducted

-0.15

ARK

-0.14

 Affero

-0.14

Anc

-0.14

xC

-0.14

POSITIVE LOGITS

addir

0.15

unsch

0.14

ãģľ

0.14

suy

0.14

Montserrat

0.14

ransition

0.13

Cong

0.13

weetalert

0.13

 Tong

0.13

Fi

0.13

Activations Density 0.018%

comparative phrases emphasizing additional qualities or quantities

No Comments

No Known Activations