INDEX

Explanations

references to ice cream and related treats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 bread

-0.19

 gravy

-0.18

ente

-0.17

enta

-0.17

amina

-0.16

 cooking

-0.15

 wines

-0.15

 frying

-0.15

 champagne

-0.15

lej

-0.15

POSITIVE LOGITS

ice

0.42

Ice

0.38

Ice

0.33

ice

0.31

åĨ°

0.25

ICE

0.25

ices

0.25

ICE

0.23

 cone

0.23

 scoop

0.23

Activations Density 0.040%

references to ice cream and related treats

No Comments

No Known Activations