INDEX

Explanations

specific words and terms related to sports and activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

so

-0.35

ness

-0.33

nya

-0.31

ìĿĦ

-0.30

ship

-0.30

sh

-0.29

son

-0.29

ne

-0.28

ser

-0.27

ss

-0.26

POSITIVE LOGITS

urope

0.21

oil

0.18

eker

0.18

iros

0.18

pond

0.18

equipment

0.17

eo

0.17

kind

0.16

anuts

0.16

aft

0.16

Activations Density 1.157%

specific words and terms related to sports and activities

No Comments

No Known Activations