INDEX

Explanations

numerical patterns and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

jo

-0.18

 proxies

-0.15

elay

-0.15

zos

-0.14

olin

-0.14

 proxy

-0.14

ies

-0.13

qm

-0.13

 conc

-0.13

jo

-0.13

POSITIVE LOGITS

 Quang

0.16

0.15

 Schneider

0.15

umbn

0.14

amental

0.14

à¥Ģà¤£

0.14

OOT

0.14

 Ansi

0.14

inou

0.14

CJK

0.14

Activations Density 0.040%

numerical patterns and symbols

No Comments

No Known Activations