INDEX

Explanations

place names and references to locations

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

inki

-0.15

'gc

-0.15

Ø·Ø¹

-0.14

 Snape

-0.14

CEED

-0.14

ovit

-0.14

NavItem

-0.14

 Lexington

-0.14

edes

-0.14

nze

-0.14

POSITIVE LOGITS

oz

0.23

ureka

0.23

Oz

0.22

0.21

 Springfield

0.19

0.18

oz

0.18

Br

0.17

¥

0.16

 ozone

0.16

Activations Density 0.014%

place names and references to locations

No Comments

No Known Activations