INDEX

Explanations

references to cocktails and mixed drinks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

lh

-0.16

inka

-0.16

 gore

-0.15

InstantiationException

-0.15

 Locker

-0.15

jed

-0.15

oins

-0.14

 potatoes

-0.14

 durum

-0.14

 Brewery

-0.14

POSITIVE LOGITS

ice

0.35

Ice

0.31

Ice

0.27

ICE

0.26

ice

0.24

ICE

0.22

åĨ°

0.19

 garn

0.19

 iceberg

0.17

 gren

0.17

Activations Density 0.056%

references to cocktails and mixed drinks

No Comments

No Known Activations