INDEX

Explanations

phrases related to significant events occurring after a specific time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ignet

-0.16

eters

-0.15

asing

-0.14

oplevel

-0.14

ibaba

-0.14

 Trophy

-0.14

 Ð·Ð½

-0.14

 Trab

-0.14

avel

-0.14

hec

-0.14

POSITIVE LOGITS

 being

0.20

 previously

0.19

 previous

0.17

being

0.16

 earlier

0.15

 Previous

0.14

Being

0.14

æĸ½

0.14

ÙħØ§

0.14

 bottles

0.14

Activations Density 0.064%

phrases related to significant events occurring after a specific time

No Comments

No Known Activations