INDEX

Explanations

expressions of personal experience and emotional reflection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

so

-0.22

å¦ĤæŃ¤

-0.18

 Ð½Ð°ÑģÑĤ

-0.18

 however

-0.17

 Recall

-0.16

 recall

-0.16

íİ

-0.16

remember

-0.16

 such

-0.15

å¿ĺ

-0.15

POSITIVE LOGITS

 doubly

0.27

 accordingly

0.25

 therefore

0.22

 Accordingly

0.21

 consequently

0.19

 essentially

0.19

kind

0.19

 basically

0.19

 Therefore

0.18

Therefore

0.18

Activations Density 0.184%

expressions of personal experience and emotional reflection

No Comments

No Known Activations