INDEX

Explanations

proper nouns, especially names and organizations

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

 Ø§ÙĦØ«

-0.15

á»Ľi

-0.15

Ã³ria

-0.15

oodle

-0.15

nton

-0.15

xBF

-0.14

_DETECT

-0.14

unei

-0.14

EventListener

-0.14

atura

-0.14

POSITIVE LOGITS

SG

0.23

AG

0.22

tog

0.21

Lag

0.21

LAG

0.20

agog

0.20

lg

0.19

Kag

0.19

AGR

0.18

LG

0.18

Activations Density 0.183%

proper nouns, especially names and organizations

No Comments

No Known Activations