INDEX

Explanations

references to food-related terms and items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

empo

-0.15

 Fauc

-0.15

\OptionsResolver

-0.15

 NOAA

-0.14

Ð½Ð¾Ð´

-0.14

ĵåĲį

-0.14

Nike

-0.14

 Helen

-0.14

 Provid

-0.14

(GPIO

-0.14

POSITIVE LOGITS

 implement

0.25

 implements

0.25

 tractor

0.24

implements

0.24

Cla

0.23

 combine

0.23

 thresh

0.23

 Combine

0.23

 Implements

0.22

 John

0.21

Activations Density 0.018%

references to food-related terms and items

No Comments

No Known Activations