INDEX

Explanations

specific geographic locations and address details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Border

-0.19

 lake

-0.18

 border

-0.17

 pond

-0.17

anic

-0.17

border

-0.17

Border

-0.16

¡

-0.16

ocommerce

-0.16

lake

-0.16

POSITIVE LOGITS

bay

0.20

 peninsula

0.20

 Peninsula

0.20

 Spit

0.18

èĥĨ

0.18

æ¹¾

0.18

 tide

0.17

pen

0.17

_COMPAT

0.17

 tidal

0.17

Activations Density 0.249%

specific geographic locations and address details

No Comments

No Known Activations