INDEX

Explanations

references to various types of facilities and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ened

-0.18

ãģĬãĤĬ

-0.17

ight

-0.17

jom

-0.16

ening

-0.16

alytics

-0.16

edException

-0.15

ane

-0.15

eenth

-0.15

edList

-0.15

POSITIVE LOGITS

ground

0.18

tes

0.17

ÑģÑĮ

0.16

uzzer

0.16

arian

0.16

/services

0.16

Verse

0.16

ally

0.15

ory

0.15

 manager

0.15

Activations Density 0.042%

references to various types of facilities and their attributes

No Comments

No Known Activations

references to various types of facilities and their attributes

No Comments

No Known Activations