INDEX

Explanations

references and citations 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 @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ankan

-0.16

 Turnbull

-0.15

hausen

-0.15

 Barcl

-0.14

ustr

-0.14

jspx

-0.14

Phi

-0.14

IO

-0.14

IE

-0.13

Assignable

-0.13

POSITIVE LOGITS

note

0.27

foot

0.21

ogram

0.17

clide

0.16

HM

0.15

ernote

0.15

reff

0.15

Note

0.15

eree

0.15

ref

0.15

Activations Density 0.001%

references and citations in academic or technical documents

No Comments

No Known Activations