INDEX

Explanations

references to films and their directors

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

-0.16

åŁº

-0.15

FormatException

-0.14

Ð¸ÑĤÐµÑĤ

-0.14

POSITE

-0.14

æĿ

-0.14

 porta

-0.14

haf

-0.13

Ð¶Ð°

-0.13

 Ingen

-0.13

POSITIVE LOGITS

 director

0.26

çĽ£çĿ£

0.25

 ê°Ĳëıħ

0.25

 coach

0.24

 manager

0.23

director

0.22

 Director

0.21

 directors

0.20

-direct

0.19

manager

0.19

Activations Density 0.170%

references to films and their directors

No Comments

No Known Activations