INDEX

Explanations

contact information and instructions for reaching various departments or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

roller

-0.17

peria

-0.17

isson

-0.15

Stencil

-0.15

uxe

-0.13

ÄŁen

-0.13

inne

-0.13

à¸²à¸¢à¸Ļ

-0.13

regon

-0.13

ux

-0.13

POSITIVE LOGITS

at

0.23

oda

0.15

 neutrality

0.14

Brun

0.14

.googlecode

0.14

werp

0.14

åĵ¦

0.14

 receptive

0.14

Activations Density 0.066%

contact information and instructions for reaching various departments or individuals

No Comments

No Known Activations