INDEX

Explanations

phrases indicating novelty or uniqueness

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

á»ĳt

-0.20

 Actual

-0.18

ê´

-0.15

ameleon

-0.14

ãĤį

-0.14

itte

-0.14

[~,

-0.14

Actual

-0.14

zeug

-0.14

à¸¥à¸ĩ

-0.14

POSITIVE LOGITS

 previously

0.34

 elsewhere

0.31

 otherwise

0.31

 previous

0.26

seen

0.25

 Previously

0.25

 seen

0.24

 else

0.24

otherwise

0.24

 before

0.23

Activations Density 0.094%

phrases indicating novelty or uniqueness

No Comments

No Known Activations