INDEX

Explanations

phrases that indicate temporal events or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

lix

-0.17

agini

-0.17

cade

-0.16

ardu

-0.15

scape

-0.15

adele

-0.15

loon

-0.15

ãģĹãĤĩãģĨ

-0.15

mente

-0.14

[rand

-0.14

POSITIVE LOGITS

soever

0.30

/if

0.23

-Ð»Ð¸Ð±Ð¾

0.22

abouts

0.22

/how

0.19

-Ð½Ð¸Ð±ÑĥÐ´ÑĮ

0.18

it

0.18

we

0.18

you

0.18

EVER

0.18

Activations Density 0.124%

phrases that indicate temporal events or conditions

No Comments

No Known Activations