INDEX

Explanations

phrases indicating descriptions and evaluations of experiences or situations

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

ëĿ¼ëıĦ

-0.15

 himself

-0.14

 ìŀĪëĭ¤ëĬĶ

-0.13

Î´Î¬

-0.13

antz

-0.13

 enumerator

-0.13

upert

-0.13

å¯Ł

-0.13

 punt

-0.12

 Ð¿Ð»Ð°ÑģÑĤÐ¸

-0.12

POSITIVE LOGITS

0.28

 Â«

0.25

"[

0.24

“

0.23

 “[

0.22

0.21

``

0.21

ãĢĮ

0.19

'[

0.19

"(

0.18

Activations Density 0.177%

phrases indicating descriptions and evaluations of experiences or situations

No Comments

No Known Activations