INDEX

Explanations

references to "twin" or "twins," indicating a focus on twin-related themes

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

ÙĬÙĪÙĨ

-0.20

regon

-0.17

edir

-0.16

ulk

-0.15

Î½ÏĦ

-0.15

alis

-0.14

ptide

-0.14

ifice

-0.14

edores

-0.14

edor

-0.14

POSITIVE LOGITS

 Peaks

0.29

ning

0.23

 Cities

0.22

Cities

0.22

 peaks

0.22

 peak

0.19

 sister

0.19

 brother

0.19

/tr

0.18

peak

0.18

Activations Density 0.009%

references to "twin" or "twins," indicating a focus on twin-related themes

No Comments

No Known Activations