INDEX

Explanations

mentions of the name "Ron."

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

oned

-0.16

growth

-0.15

-0.14

inas

-0.14

inos

-0.14

icÃŃ

-0.14

angler

-0.14

wang

-0.14

å¸

-0.14

inois

-0.14

POSITIVE LOGITS

ald

0.32

aldo

0.23

aldi

0.22

nelly

0.21

ning

0.20

ninger

0.19

ny

0.19

nie

0.19

ningen

0.18

NING

0.17

Activations Density 0.007%

mentions of the name "Ron."

No Comments

No Known Activations