INDEX

Explanations

references to quantities, particularly numbers and their relations

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

ë¦½

-0.16

Ð½Ð°ÑĤ

-0.15

ocommerce

-0.15

BarItem

-0.15

iez

-0.14

InterfaceOrientation

-0.14

INTR

-0.14

_redirect

-0.14

bine

-0.14

egis

-0.14

POSITIVE LOGITS

ulton

0.15

 konce

0.14

 NotSupportedException

0.14

arrow

0.14

CRET

0.14

rips

0.14

rone

0.14

[=[

0.13

 Bones

0.13

Cle

0.13

Activations Density 0.051%

references to quantities, particularly numbers and their relations

No Comments

No Known Activations