INDEX

Explanations

references to cooking or chefs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.15

otope

-0.14

 Coast

-0.14

ayout

-0.14

itution

-0.14

isia

-0.14

AYOUT

-0.14

.sg

-0.14

afc

-0.13

oling

-0.13

POSITIVE LOGITS

sey

0.29

son

0.25

ery

0.23

ware

0.21

ingham

0.20

ERY

0.19

stown

0.18

seys

0.17

sville

0.17

iel

0.17

Activations Density 0.007%

references to cooking or chefs

No Comments

No Known Activations