INDEX

Explanations

abbreviations and acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

è¶³

-0.15

etur

-0.15

uisine

-0.14

itary

-0.14

.SuspendLayout

-0.14

okit

-0.14

 unthinkable

-0.14

 Wallace

-0.13

ifar

-0.13

 Guill

-0.13

POSITIVE LOGITS

.inflate

0.14

_GB

0.14

-lfs

0.14

Ĭ

0.14

avar

0.13

Ð²ÑĸÐ»ÑĮ

0.13

à¸±à¸Ļà¸¡

0.13

clo

0.13

 YYSTACK

0.13

eoq

0.12

Activations Density 0.098%

abbreviations and acronyms

No Comments

No Known Activations