INDEX

Explanations

punctuation marks and formatting elements in the text

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

res

-0.15

Toolkit

-0.14

SCRIPTION

-0.14

 Mojo

-0.13

 comp

-0.13

 Pere

-0.13

.damage

-0.13

è·Ŀ

-0.13

charm

-0.13

à¤¾à¤®

-0.13

POSITIVE LOGITS

olini

0.15

lisi

0.15

rani

0.15

 Å¡p

0.14

 Colony

0.14

iaux

0.14

irma

0.13

ovich

0.13

rtl

0.13

prus

0.13

Activations Density 0.641%

punctuation marks and formatting elements in the text

No Comments

No Known Activations