INDEX

Explanations

terms related to fluctuations or variations

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

ÄĻk

-0.17

OAD

-0.17

 âĹĦ

-0.15

 Ð²Ð·

-0.14

amilia

-0.14

ÐµÐ»ÑĮÐ·Ñı

-0.14

Kod

-0.14

ukan

-0.14

izzato

-0.14

Bes

-0.14

POSITIVE LOGITS

OWL

0.15

forums

0.15

ÐµÐ¼Ð¾Ð½

0.15

ÚĨÙĩ

0.14

ahun

0.14

IPA

0.14

Ø¨Ø·

0.14

 Topic

0.14

gate

0.14

erin

0.14

Activations Density 0.021%

terms related to fluctuations or variations

No Comments

No Known Activations