INDEX

Explanations

phrases that describe processes and actions related to involvement or engagement in activities

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

assin

-0.19

 Ð¶Ðµ

-0.15

ian

-0.15

 svÅ¯j

-0.15

Ð¾Ð´Ð¸

-0.15

umer

-0.14

anium

-0.14

å®¶çļĦ

-0.14

ymb

-0.13

redient

-0.13

POSITIVE LOGITS

 only

0.19

 both

0.19

 ÑģÐ¾Ð±Ð¾Ð¹

0.18

 elements

0.17

 besides

0.17

 lots

0.17

 mainly

0.17

 fewer

0.17

 mostly

0.16

Activations Density 0.198%

phrases that describe processes and actions related to involvement or engagement in activities

No Comments

No Known Activations