INDEX

Explanations

numerical values and measurements, particularly in relation to distances and weights

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

oose

-0.16

igg

-0.15

 already

-0.15

 either

-0.15

Hao

-0.14

rian

-0.14

ues

-0.14

eyh

-0.14

£½

-0.14

ESCO

-0.14

POSITIVE LOGITS

or

0.17

logic

0.15

Ð°ÑĢÐ¾Ð´

0.15

StackNavigator

0.15

erra

0.14

bcm

0.14

ãĤ¹ãĥĨ

0.14

Lon

0.14

¶ģ

0.14

anca

0.13

Activations Density 0.031%

numerical values and measurements, particularly in relation to distances and weights

No Comments

No Known Activations