INDEX

Explanations

references to academic citations and associated numerical data

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

ansi

-0.16

lap

-0.15

nda

-0.15

kazy

-0.14

udos

-0.14

pite

-0.14

 Todd

-0.14

reo

-0.14

ansk

-0.14

ÐļÐŀ

-0.14

POSITIVE LOGITS

 jour

0.15

tp

0.15

-addon

0.14

ableView

0.14

Ã¢m

0.14

à¤¾à¤ī

0.14

 Consultant

0.14

0.13

 correctness

0.13

(Controller

0.13

Activations Density 0.010%

references to academic citations and associated numerical data

No Comments

No Known Activations