INDEX

Explanations

significant terms related to beginnings and endings in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

agger

-0.17

Sag

-0.16

 aggress

-0.15

Ø¯Ø§Ø¯

-0.15

yt

-0.14

/lists

-0.14

 Fleming

-0.14

 ÑĩÑĤ

-0.13

.Immutable

-0.13

POSITIVE LOGITS

.future

0.23

 future

0.20

 tomorrow

0.19

future

0.18

 soon

0.18

soon

0.17

Âłtom

0.17

 Future

0.16

omor

0.16

Ã¤d

0.16

Activations Density 0.229%

significant terms related to beginnings and endings in various contexts

No Comments

No Known Activations