INDEX

Explanations

references to storytelling and service-related actions or announcements

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

osc

-0.17

ering

-0.16

CALE

-0.15

usta

-0.14

.weapon

-0.14

aming

-0.14

elper

-0.14

à¹ģà¸Ĺ

-0.14

>NN

-0.14

oge

-0.14

POSITIVE LOGITS

!(

0.15

//~

0.14

ba

0.14

 padd

0.14

 Jewel

0.14

 arbitrary

0.14

_UNS

0.14

ev

0.14

Activations Density 0.013%

references to storytelling and service-related actions or announcements

No Comments

No Known Activations