INDEX

Explanations

acronyms and abbreviations related to news organizations

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

ips

-0.16

agne

-0.15

abile

-0.15

-0.14

ipse

-0.14

icl

-0.14

contra

-0.14

ÛĮÙĩ

-0.14

ible

-0.13

ooth

-0.13

POSITIVE LOGITS

utan

0.15

upe

0.14

rych

0.14

å¸Į

0.14

obus

0.14

HomeAsUp

0.14

STR

0.14

etta

0.14

odian

0.13

utsch

0.13

Activations Density 0.002%

acronyms and abbreviations related to news organizations

No Comments

No Known Activations