INDEX

Explanations

mentions of the name "Evan" or related variations throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

edef

-0.15

Ø§Ø¦Ø¹

-0.15

vej

-0.15

iffies

-0.15

atsu

-0.15

aticon

-0.14

Ñŀ

-0.14

raphics

-0.14

.epsilon

-0.14

_interaction

-0.14

POSITIVE LOGITS

Ev

0.23

ev

0.21

angel

0.19

olution

0.19

gen

0.18

angep

0.17

ett

0.17

OLUTION

0.17

.ev

0.16

EV

0.16

Activations Density 0.022%

mentions of the name "Evan" or related variations throughout the text

No Comments

No Known Activations