INDEX

Explanations

acronyms and abbreviations related to academic degrees and professional titles

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

Ð¿ÑĢÐ°Ð²

-0.15

issen

-0.14

sys

-0.14

ãĤĦãģĻ

-0.14

ØªÙĩ

-0.14

.lookup

-0.14

ous

-0.14

Äĩ

-0.14

ffer

-0.13

à¸«à¸Ļ

-0.13

POSITIVE LOGITS

stra

0.16

haar

0.16

igans

0.14

hyth

0.14

RON

0.14

icorn

0.14

imiz

0.14

AO

0.13

baugh

0.13

iez

0.13

Activations Density 0.033%

acronyms and abbreviations related to academic degrees and professional titles

No Comments

No Known Activations