INDEX

Explanations

acronyms and abbreviations related to technical and regulatory subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ahun

-0.15

 defaultManager

-0.15

ÙĦÛĮØ³ÛĮ

-0.14

leyen

-0.14

owler

-0.14

uala

-0.14

_CHARS

-0.14

ÐĲÑĢÑħÑĸÐ²

-0.14

addock

-0.14

jez

-0.14

POSITIVE LOGITS

0.17

 strateg

0.15

0.14

ses

0.14

Fo

0.14

ffer

0.13

coop

0.13

andon

0.13

ions

0.13

Activations Density 0.306%

acronyms and abbreviations related to technical and regulatory subjects

No Comments

No Known Activations