INDEX

Explanations

mathematical concepts or terms related to sets and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

egers

-0.15

 ÙħØ§Ùĩ

-0.15

à¸Ħ

-0.15

oop

-0.14

ank

-0.14

ma

-0.14

abo

-0.14

anks

-0.14

ma

-0.13

reh

-0.13

POSITIVE LOGITS

Ã«r

0.16

ko

0.15

KO

0.15

ALLED

0.15

ãģ¡ãĤī

0.15

 strictly

0.14

airo

0.14

 Dahl

0.14

ahan

0.14

nod

0.14

Activations Density 0.023%

mathematical concepts or terms related to sets and their properties

No Comments

No Known Activations