INDEX

Explanations

instructions and processes related to cooking and food preparation

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

 blown

-0.17

oric

-0.15

áº½

-0.15

emoc

-0.14

.Persistent

-0.14

ÐµÑĢÐµÐ¶

-0.14

ients

-0.14

irting

-0.14

ÐĴÑĤ

-0.13

LEAN

-0.13

POSITIVE LOGITS

sit

0.28

 overnight

0.28

 cool

0.27

 sitting

0.26

 cooling

0.25

cool

0.25

 Overnight

0.24

Cool

0.23

 Cooling

0.23

 steep

0.23

Activations Density 0.053%

instructions and processes related to cooking and food preparation

No Comments

No Known Activations