INDEX

Explanations

variations and forms of the word "free" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

sell

-0.19

ernal

-0.19

son

-0.19

sm

-0.17

si

-0.17

 Bloss

-0.17

ska

-0.16

rocket

-0.16

 Suff

-0.16

sen

-0.16

POSITIVE LOGITS

estyle

0.26

est

0.25

ighting

0.25

ighth

0.24

ights

0.24

ck

0.23

esty

0.21

eways

0.21

nds

0.20

eware

0.19

Activations Density 0.004%

variations and forms of the word "free" in different contexts

No Comments

No Known Activations