INDEX

Explanations

references to the word "Arm" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

erne

-0.16

erate

-0.15

osi

-0.15

Touches

-0.15

 Anita

-0.15

ernen

-0.14

lew

-0.14

iating

-0.14

ews

-0.14

inis

-0.14

POSITIVE LOGITS

chair

0.25

oured

0.24

aments

0.23

strong

0.22

ament

0.19

ature

0.19

stead

0.19

stadt

0.19

ored

0.18

atures

0.18

Activations Density 0.013%

references to the word "Arm" and its variations in various contexts

No Comments

No Known Activations