INDEX

Explanations

elements and structures in code, particularly related to JSON or object notation syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ÑģÐ»Ð¸

-0.17

icari

-0.16

ÐµÑģÑı

-0.15

Ã¨s

-0.15

ohn

-0.14

uten

-0.14

yps

-0.14

avir

-0.14

å§Ĭ

-0.14

cej

-0.14

POSITIVE LOGITS

0.23

0.19

bish

0.17

0.16

ajs

0.15

ancel

0.15

aj

0.15

oldt

0.15

ecn

0.14

AREST

0.14

Activations Density 0.114%

elements and structures in code, particularly related to JSON or object notation syntax

No Comments

No Known Activations