INDEX

Explanations

questions and discussions about compromise and simplicity in decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

alon

-0.16

liÅ¾

-0.15

nonnull

-0.15

_compat

-0.15

Ã²ng

-0.14

 compl

-0.14

alus

-0.14

yles

-0.14

jeme

-0.14

anford

-0.14

POSITIVE LOGITS

 simply

0.54

 Simply

0.43

 simplement

0.42

Simply

0.40

 Ð¿ÑĢÐ¾ÑģÑĤÐ¾

0.37

 just

0.34

 einfach

0.33

 ê·¸ëĥ¥

0.30

çĽ´æİ¥

0.30

 simples

0.29

Activations Density 0.214%

questions and discussions about compromise and simplicity in decision-making

No Comments

No Known Activations