INDEX

Explanations

mentions of locations and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Rutgers

-0.16

Ont

-0.16

otre

-0.16

 Guinea

-0.15

 reco

-0.15

 Rhode

-0.15

 Ontario

-0.15

Tup

-0.15

_CODEC

-0.15

ilib

-0.15

POSITIVE LOGITS

 Calgary

0.44

 Alberta

0.40

Albert

0.39

 Albert

0.28

 Edmonton

0.28

 Stamp

0.26

Bow

0.25

 Sadd

0.24

Cal

0.24

 Alberto

0.23

Activations Density 0.130%

mentions of locations and addresses

No Comments

No Known Activations