INDEX

Explanations

brand names and references to companies or products

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

agra

-0.16

igua

-0.15

activex

-0.15

 jurisdictions

-0.15

ìĤ¬ë¬´

-0.14

ipi

-0.14

isle

-0.14

activ

-0.14

wg

-0.14

abol

-0.13

POSITIVE LOGITS

alan

0.15

ibold

0.15

ignet

0.15

vik

0.14

_NEAR

0.14

 Aster

0.14

Rab

0.14

ensburg

0.14

banner

0.13

ACS

0.13

Activations Density 0.056%

brand names and references to companies or products

No Comments

No Known Activations