INDEX

Explanations

phrases indicating time and past events or changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 soon

-0.29

soon

-0.25

 currently

-0.23

 finally

-0.21

now

-0.21

currently

-0.20

 recently

-0.20

çĽ®åīį

-0.20

finally

-0.19

 ultimately

-0.18

POSITIVE LOGITS

 merely

0.24

 simply

0.22

 solely

0.20

 only

0.19

(before

0.18

 thought

0.18

 simplement

0.17

 Ø¨ÙĪØ¯Ùĩ

0.17

 Ð¿ÑĢÐ¾ÑģÑĤÐ¾

0.17

 iken

0.16

Activations Density 0.229%

phrases indicating time and past events or changes

No Comments

No Known Activations