INDEX

Explanations

references to specific dates and time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

pus

-0.18

ynet

-0.15

orum

-0.14

fel

-0.14

emet

-0.13

 repost

-0.13

dni

-0.13

hel

-0.13

Prev

-0.13

fel

-0.13

POSITIVE LOGITS

 until

0.37

 till

0.37

 onwards

0.36

 hasta

0.33

 jusqu

0.31

until

0.28

 atÃ©

0.28

 Until

0.27

 perspective

0.26

Until

0.26

Activations Density 0.074%

references to specific dates and time periods

No Comments

No Known Activations