INDEX

Explanations

numerical sequences and values within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

../../../

-0.21

fold

-0.21

-quarters

-0.19

ihan

-0.18

elson

-0.17

iy

-0.16

fall

-0.16

rd

-0.16

Û°Û°

-0.16

../../

-0.16

POSITIVE LOGITS

nd

0.57

nds

0.30

ND

0.28

Ð½Ð´

0.24

nder

0.23

0.22

-thirds

0.22

nde

0.22

nda

0.21

nd

0.20

Activations Density 0.171%

numerical sequences and values within the text

No Comments

No Known Activations