INDEX

Explanations

detailed descriptions of travel itineraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

addir

-0.17

ourg

-0.15

á»ħ

-0.15

zenÃŃ

-0.15

Ans

-0.15

_EMIT

-0.14

ÑĥÐ»Ð°

-0.14

edBy

-0.14

Addon

-0.14

Writable

-0.14

POSITIVE LOGITS

 ports

0.18

 port

0.17

Trace

0.16

 Ports

0.16

 Stops

0.16

Civ

0.15

Ports

0.15

 Trace

0.15

ResponseBody

0.15

-port

0.15

Activations Density 0.008%

detailed descriptions of travel itineraries

No Comments

No Known Activations