INDEX

Explanations

descriptions of food and cooking methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

IgnoreCase

-0.14

 based

-0.14

affle

-0.13

 prof

-0.13

jud

-0.13

 Autof

-0.13

 infused

-0.13

à¥Ĥà¤Ł

-0.13

aunch

-0.13

 Gors

-0.12

POSITIVE LOGITS

 alone

0.28

alone

0.27

 Alone

0.27

 solo

0.24

 accompany

0.23

 alongside

0.23

-alone

0.22

ä½ľä¸º

0.22

 either

0.21

 accompanies

0.21

Activations Density 0.111%

descriptions of food and cooking methods

No Comments

No Known Activations