INDEX

Explanations

phrases and actions related to user interface options, particularly checkboxes and user settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

istÃ©

-0.15

ivol

-0.15

.jetbrains

-0.14

ossal

-0.14

 Ø§ÙĦØµÙĨ

-0.14

ÃŃda

-0.14

ÑĢÑĸÐ·

-0.14

letcher

-0.14

ingu

-0.14

uito

-0.13

POSITIVE LOGITS

asper

0.17

0.15

ãĥ¼ãĥł

0.15

ripsi

0.14

 WCHAR

0.14

ipel

0.14

 ìĸ¸

0.14

ATALOG

0.14

\Eloquent

0.14

Muon

0.13

Activations Density 0.051%

phrases and actions related to user interface options, particularly checkboxes and user settings

No Comments

No Known Activations