INDEX

Explanations

references to chapters and sections in academic or technical documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

xoops

-0.16

ighet

-0.15

igel

-0.15

IPH

-0.14

IGH

-0.14

enburg

-0.14

chio

-0.14

bla

-0.14

osi

-0.14

compiler

-0.14

POSITIVE LOGITS

ise

0.16

à¹ĭ

0.15

aces

0.15

Å©

0.15

azzi

0.15

anie

0.14

izm

0.14

 branch

0.14

ugin

0.14

amon

0.14

Activations Density 0.017%

references to chapters and sections in academic or technical documents

No Comments

No Known Activations