INDEX

Explanations

variations of the verb "to be" in different tenses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ãĤ¤ãĥī

-0.15

ENÃį

-0.15

TriState

-0.15

£½

-0.14

Indented

-0.14

ÎµÏį

-0.14

Ã©ra

-0.14

aset

-0.14

ÐµÑĢÐ³

-0.14

reeNode

-0.14

POSITIVE LOGITS

 able

0.25

 forced

0.18

 allowed

0.18

 revealed

0.17

 unable

0.16

 ready

0.16

 born

0.16

iban

0.15

 permitted

0.15

 heard

0.15

Activations Density 0.300%

variations of the verb "to be" in different tenses

No Comments

No Known Activations