INDEX

Explanations

terms related to phonetics and pronunciation rules

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

indsight

-0.12

essim

-0.11

æ´ŀ

-0.11

ä¼ģ

-0.11

mdp

-0.11

æŀĿ

-0.10

rief

-0.10

Ð»Ð°Ð·

-0.10

untos

-0.10

emento

-0.10

POSITIVE LOGITS

 pronunciation

0.43

 spelling

0.43

 gramm

0.40

 grammar

0.39

 spell

0.38

 Grammar

0.36

 pronounce

0.35

 pron

0.34

 phon

0.34

 vowel

0.34

Activations Density 1.239%

terms related to phonetics and pronunciation rules

No Comments

No Known Activations

terms related to phonetics and pronunciation rules

No Comments

No Known Activations