INDEX

Explanations

references to historical leaders and significant political events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

arser

-0.16

ãģĭãģ£ãģ¦

-0.15

adle

-0.15

 stew

-0.15

 Ø³Ø±Ø¯

-0.15

aceae

-0.14

 Stretch

-0.14

kke

-0.13

.Append

-0.13

echa

-0.13

POSITIVE LOGITS

 reform

0.68

 reforms

0.64

 Reform

0.57

æĶ¹éĿ©

0.49

 Ø§ØµÙĦØ§ØŃ

0.30

 structural

0.29

 overhaul

0.27

 Structural

0.27

 priv

0.24

 modern

0.23

Activations Density 0.216%

references to historical leaders and significant political events

No Comments

No Known Activations

references to historical leaders and significant political events

No Comments

No Known Activations