INDEX

Explanations

questions or requests for clarification from the reader

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

emez

-0.19

ãĥĥãĤ°

-0.15

allee

-0.15

chner

-0.15

achi

-0.14

ani

-0.14

(dead

-0.14

urring

-0.13

inois

-0.13

attern

-0.13

POSITIVE LOGITS

 really

0.28

 Really

0.25

 seriously

0.25

 Seriously

0.25

really

0.24

Seriously

0.23

Really

0.23

æľ¬å½ĵãģ«

0.23

 wirklich

0.21

çľŁçļĦ

0.21

Activations Density 0.116%

questions or requests for clarification from the reader

No Comments

No Known Activations