INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

oader

-0.18

ernel

-0.17

spo

-0.15

chet

-0.15

opher

-0.15

ermo

-0.14

ald

-0.14

 Newtown

-0.14

unfinished

-0.14

aldo

-0.14

POSITIVE LOGITS

.Networking

0.16

fak

0.15

elli

0.15

eworld

0.14

 bail

0.14

izr

0.13

adro

0.13

äº

0.13

iasi

0.13

ãģĵãĤĵãģª

0.13

Activations Density 0.118%

expressions of gratitude and appreciation

No Comments

No Known Activations