INDEX

Explanations

rhetorical questions or expressions of surprise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

gni

-0.16

eniable

-0.15

enty

-0.14

nio

-0.14

 anything

-0.14

ulty

-0.14

mie

-0.14

ito

-0.14

emonic

-0.14

ä¹ħ

-0.14

POSITIVE LOGITS

 else

0.21

do

0.20

aya

0.19

did

0.19

 better

0.18

 timing

0.18

timing

0.17

soever

0.17

ser

0.16

	else

0.15

Activations Density 0.083%

rhetorical questions or expressions of surprise

No Comments

No Known Activations