INDEX

Explanations

references to specific names and places, particularly those related to events and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 trades

-0.17

annie

-0.16

unist

-0.15

rchive

-0.15

’yi

-0.14

 Trades

-0.14

stad

-0.14

inous

-0.14

eket

-0.14

-syntax

-0.14

POSITIVE LOGITS

ban

0.33

ben

0.24

iben

0.22

iban

0.22

ìĹĲìĦľ

0.19

ìĹĲìĦľëıĦ

0.18

aban

0.18

Ban

0.18

Ban

0.17

-b

0.17

Activations Density 0.003%

references to specific names and places, particularly those related to events and institutions

No Comments

No Known Activations