INDEX

Explanations

articles and specific instances of the word "a" 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 @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ordum

-0.15

ule

-0.15

ULE

-0.14

-ÑĤÐ°ÐºÐ¸

-0.13

rossover

-0.13

ucken

-0.13

 ÎĵÎ¹

-0.13

Ð°ÑĢÐ¸

-0.13

åģĩ

-0.13

olo

-0.13

POSITIVE LOGITS

.k

0.32

 fact

0.31

 feat

0.24

fact

0.22

KA

0.22

 testament

0.21

 circumstance

0.20

 result

0.20

 indication

0.20

nd

0.20

Activations Density 0.131%

articles and specific instances of the word "a" in various contexts

No Comments

No Known Activations