INDEX

Explanations

occurrences of significant events or milestones

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

ãĤ¤ãĥ³ãĥĪ

-0.18

.Management

-0.15

ssi

-0.15

argins

-0.15

IfExists

-0.15

-0.14

æĸ½

-0.14

Ð¸Ð½Ð³

-0.14

Poh

-0.14

\Blueprint

-0.14

POSITIVE LOGITS

 poprvÃ©

0.42

 Ð²Ð¿

0.42

for

0.41

for

0.33

 first

0.32

 láº§n

0.32

 fÃ¸rste

0.31

 pela

0.31

 ÙĦØ£

0.30

ç¬¬ä¸Ģæ¬¡

0.29

Activations Density 0.287%

occurrences of significant events or milestones

No Comments

No Known Activations