INDEX

Explanations

references to nutritional content and its related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

hem

-0.21

esty

-0.18

aign

-0.17

-0.16

haf

-0.16

ãĥ¼ãĥŃ

-0.15

vinces

-0.15

awy

-0.14

leck

-0.14

ï¸ı

-0.14

POSITIVE LOGITS

ritional

0.33

meg

0.33

ty

0.31

rients

0.26

shell

0.25

rition

0.24

ella

0.24

rient

0.23

Meg

0.23

ters

0.22

Activations Density 0.006%

references to nutritional content and its related terms

No Comments

No Known Activations