INDEX

Explanations

geographic locations and references within a specific context

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

 à¸¿

-0.15

resden

-0.15

LEC

-0.15

Ø§Ø¨ÙĦ

-0.15

andom

-0.15

drv

-0.15

isay

-0.15

 Revel

-0.15

 Nielsen

-0.14

rawler

-0.14

POSITIVE LOGITS

 Stuttgart

0.26

 Neck

0.25

Bad

0.20

 Rosenstein

0.20

lsruhe

0.19

Bad

0.18

lingen

0.18

alem

0.18

inate

0.17

 Basel

0.17

Activations Density 0.013%

geographic locations and references within a specific context

No Comments

No Known Activations