INDEX

Explanations

instructions related to cooking methods and techniques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ot

-0.16

ete

-0.15

 growth

-0.15

-0.14

en

-0.14

 Growth

-0.14

 Compet

-0.14

 distortion

-0.14

 Bash

-0.14

 polished

-0.14

POSITIVE LOGITS

/loose

0.20

ANGO

0.19

 thick

0.18

 Thick

0.17

 batter

0.17

Mou

0.16

 Batter

0.16

 consistency

0.16

OPSIS

0.16

roperty

0.15

Activations Density 0.037%

instructions related to cooking methods and techniques

No Comments

No Known Activations