INDEX

Explanations

specific dates and references to time-related events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

endi

-0.16

inde

-0.16

 KÃ¼r

-0.15

 indeed

-0.15

 accordingly

-0.14

hang

-0.13

foon

-0.13

 Ø´Ø§Ø®

-0.13

Å¡Å¥

-0.13

 aspir

-0.12

POSITIVE LOGITS

 downtown

0.23

 Downtown

0.20

 County

0.19

 Township

0.19

town

0.18

 district

0.18

 District

0.17

 Historic

0.17

-town

0.17

istrict

0.17

Activations Density 0.073%

specific dates and references to time-related events

No Comments

No Known Activations