INDEX

Explanations

references to specific years, particularly focusing on the year 2019

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

çĽĺ

-0.16

ibel

-0.15

illard

-0.15

Ã©rt

-0.15

uga

-0.14

 Williamson

-0.14

arra

-0.14

olar

-0.14

ou

-0.14

Kil

-0.13

POSITIVE LOGITS

theid

0.17

otten

0.16

omens

0.15

ovÃŃ

0.15

vars

0.14

rut

0.14

åħī

0.14

ãĤ¤ãĤ¹

0.14

TO

0.14

mont

0.14

Activations Density 0.045%

references to specific years, particularly focusing on the year 2019

No Comments

No Known Activations