INDEX

Explanations

phrases related to establishing or organizing structures, systems, or plans

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ouver

-0.16

ä¸Ī

-0.15

 Hang

-0.15

Ð¾Ð´Ñĭ

-0.15

Æ°ng

-0.15

ColumnsMode

-0.15

icare

-0.14

atoire

-0.14

IColor

-0.14

Ð±ÑĢÐ°

-0.14

POSITIVE LOGITS

eldon

0.18

mae

0.14

hs

0.14

ì´

0.14

UDGE

0.13

ahn

0.13

Pi

0.13

 èĮ

0.13

eni

0.13

gfx

0.13

Activations Density 0.038%

phrases related to establishing or organizing structures, systems, or plans

No Comments

No Known Activations