INDEX

Explanations

details about bonus features and additional content related to DVD releases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 ilma

-0.16

bakan

-0.15

çīĮ

-0.15

opolitan

-0.15

abis

-0.14

imest

-0.14

avez

-0.14

 Policy

-0.14

abajo

-0.14

POSITIVE LOGITS

 deleted

0.23

 Deleted

0.22

Deleted

0.20

deleted

0.20

 feature

0.19

 interviews

0.19

 behind

0.18

 commentary

0.18

feature

0.17

 interview

0.17

Activations Density 0.012%

details about bonus features and additional content related to DVD releases

No Comments

No Known Activations