INDEX

Explanations

descriptions of travel destinations and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 builtin

-0.14

iese

-0.14

ournemouth

-0.14

urch

-0.14

/Foundation

-0.13

alsa

-0.13

Tower

-0.13

ipsis

-0.13

/Common

-0.13

 Functions

-0.13

POSITIVE LOGITS

 bucket

0.21

 Bucket

0.20

bucket

0.17

 UNESCO

0.17

 destinations

0.17

spo

0.17

_bucket

0.17

UCKET

0.16

 destination

0.16

APSHOT

0.15

Activations Density 0.087%

descriptions of travel destinations and experiences

No Comments

No Known Activations