INDEX

Explanations

references to specific time frames and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

now

-0.25

 lately

-0.22

 recent

-0.20

 currently

-0.20

 ÑģÐµÐ¹ÑĩÐ°Ñģ

-0.20

 today

-0.20

 recently

-0.20

çİ°åľ¨

-0.20

 Ø§ÙĦØ¢ÙĨ

-0.20

çı¾åľ¨

-0.19

POSITIVE LOGITS

 instead

0.23

instead

0.22

 again

0.21

Instead

0.21

 Instead

0.20

Again

0.18

 focus

0.18

again

0.17

 Again

0.17

 focuses

0.17

Activations Density 0.149%

references to specific time frames and events

No Comments

No Known Activations