INDEX

Explanations

negative or cautionary statements related to physical constraints or limitations

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

ania

-0.15

@js

-0.15

erli

-0.15

Rah

-0.15

 hÃ£

-0.15

 neut

-0.14

 Ulus

-0.14

lauf

-0.14

oggles

-0.14

 Ramp

-0.14

POSITIVE LOGITS

 snag

0.25

 bunch

0.23

sag

0.21

 pills

0.20

 dent

0.20

rub

0.19

 scratching

0.19

 chip

0.18

dent

0.18

Scr

0.18

Activations Density 0.099%

negative or cautionary statements related to physical constraints or limitations

No Comments

No Known Activations