INDEX

Explanations

references to honors and awards

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

eum

-0.18

æĪ¸

-0.17

ture

-0.15

lÃ¡n

-0.15

isme

-0.15

eah

-0.15

ENDING

-0.14

oje

-0.14

hood

-0.14

tone

-0.14

POSITIVE LOGITS

orary

0.32

olulu

0.27

orable

0.23

esty

0.20

ours

0.20

ored

0.20

oring

0.19

soever

0.19

obody

0.19

ky

0.18

Activations Density 0.007%

references to honors and awards

No Comments

No Known Activations