INDEX

Explanations

mathematical symbols and representations related to equations and variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

tica

-0.17

ombo

-0.16

atica

-0.15

adium

-0.14

 PoÄįet

-0.14

amo

-0.14

allele

-0.14

jumbotron

-0.13

çĭĤ

-0.13

kke

-0.13

POSITIVE LOGITS

Ð¼ÐµÐ½Ð¸

0.15

isposable

0.15

vette

0.14

OpenHelper

0.14

-stats

0.14

ichert

0.14

Ð»ÑĥÑĪ

0.14

ãģ³

0.14

 eldre

0.14

 Vict

0.14

Activations Density 0.062%

mathematical symbols and representations related to equations and variables

No Comments

No Known Activations