INDEX

Explanations

references 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 @ 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

-cookie

-0.17

tura

-0.16

AGMA

-0.16

Ð»Ð¸Ñı

-0.15

 addCriterion

-0.15

ØŃÙĩ

-0.15

URA

-0.15

 cocoa

-0.15

-expand

-0.14

 Chandler

-0.14

POSITIVE LOGITS

 cruc

0.23

 Brass

0.21

 brass

0.21

 Brussels

0.20

 Cruc

0.20

 broccoli

0.19

 greens

0.17

rad

0.17

 cabbage

0.17

 iceberg

0.17

Activations Density 0.084%

references to cooking and food preparation

No Comments

No Known Activations