INDEX

Explanations

expressions of gratitude and requests for help or clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ustil

-0.18

pip

-0.17

Pip

-0.17

odo

-0.15

anton

-0.15

Coder

-0.15

ettel

-0.15

-0.14

geois

-0.14

rol

-0.14

POSITIVE LOGITS

LIK

0.15

Thy

0.15

èĪŀ

0.14

eni

0.14

asa

0.14

ÐľÐŀ

0.14

yor

0.14

vos

0.14

vale

0.14

osi

0.14

Activations Density 0.001%

expressions of gratitude and requests for help or clarification

No Comments

No Known Activations