INDEX

Explanations

names and political affiliations related to governance and public policy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ã¡no

-0.15

toISOString

-0.14

enson

-0.14

cono

-0.13

Î¿Î»

-0.13

 createState

-0.13

 realise

-0.13

tot

-0.13

passes

-0.12

 ÑģÑĤÐ°Ð½Ð¾Ð²Ð¸ÑĤÑĮ

-0.12

POSITIVE LOGITS

 last

0.24

 earlier

0.22

 faces

0.22

 previously

0.21

 this

0.20

 frequently

0.19

 spar

0.18

 infuri

0.17

 regularly

0.17

 initially

0.17

Activations Density 0.158%

names and political affiliations related to governance and public policy

No Comments

No Known Activations