INDEX

Explanations

different forms of parentheses and their usage

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

Ã©li

-0.17

entials

-0.15

eros

-0.14

.esp

-0.14

eness

-0.14

elin

-0.14

udded

-0.14

ouz

-0.14

aub

-0.14

ente

-0.14

POSITIVE LOGITS

Fay

0.16

agic

0.16

umm

0.15

 MASK

0.15

ATK

0.14

ÚĺÛĮ

0.14

Cas

0.13

Î»ÏĮ

0.13

Topology

0.13

 Eden

0.13

Activations Density 0.040%

different forms of parentheses and their usage

No Comments

No Known Activations