INDEX

Explanations

instances of the word "complete" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

lo

-0.18

ses

-0.17

la

-0.16

se

-0.16

sin

-0.15

jem

-0.15

land

-0.14

day

-0.14

 Wich

-0.14

loc

-0.14

POSITIVE LOGITS

/full

0.21

 opposite

0.21

-package

0.19

 strangers

0.19

coverage

0.19

ledged

0.19

 Streets

0.18

 Freund

0.17

 absence

0.17

 fled

0.17

Activations Density 0.033%

instances of the word "complete" and its variations

No Comments

No Known Activations

instances of the word "complete" and its variations

No Comments

No Known Activations