INDEX

Explanations

occurrences of the word "Fern" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

tems

-0.16

arding

-0.16

leck

-0.14

itioner

-0.14

åĿĬ

-0.14

 Harding

-0.14

mond

-0.14

zent

-0.14

 heir

-0.13

pn

-0.13

POSITIVE LOGITS

Ã¡ndez

0.30

andez

0.29

sehen

0.24

ando

0.22

inand

0.22

andes

0.22

Ã£o

0.19

andom

0.19

ao

0.18

ANDOM

0.17

Activations Density 0.007%

occurrences of the word "Fern" and its variations

No Comments

No Known Activations