INDEX

Explanations

expressions of gratitude and positive experiences related to service or help received

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

athom

-0.14

ahas

-0.14

edar

-0.14

 Schwe

-0.14

inem

-0.14

ditor

-0.13

ega

-0.13

enia

-0.13

apel

-0.13

åĭ

-0.13

POSITIVE LOGITS

 NavParams

0.20

arts

0.19

 opak

0.17

arkin

0.15

FIR

0.14

ARP

0.14

åĤ¬

0.14

Pag

0.13

 Canter

0.13

 outstanding

0.13

Activations Density 0.100%

expressions of gratitude and positive experiences related to service or help received

No Comments

No Known Activations