INDEX

Explanations

elements related to years and dates in a historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

cade

-0.16

ITY

-0.16

-0.15

CV

-0.15

oba

-0.15

_MODULES

-0.15

nge

-0.15

adesh

-0.14

Boot

-0.14

adia

-0.14

POSITIVE LOGITS

 Belarus

0.37

 Belg

0.23

 Pins

0.22

bel

0.21

Bel

0.21

 Ð±ÑĸÐ»

0.21

 Ð±ÐµÐ»

0.19

Bel

0.19

BEL

0.18

 ÐĳÐµÐ»

0.18

Activations Density 0.015%

elements related to years and dates in a historical context

No Comments

No Known Activations