INDEX

Explanations

instances of the word "nu" and its variations, indicating a focus on terms related to nuanced or complex discussions

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

 Robbins

-0.18

ÅĽci

-0.14

 mand

-0.14

Ø´ÙĬ

-0.14

baugh

-0.14

anine

-0.14

optera

-0.14

atham

-0.14

Ã¦r

-0.14

POSITIVE LOGITS

vem

0.20

ismatic

0.18

ascimento

0.18

NU

0.18

clide

0.18

Nu

0.17

Nu

0.17

veau

0.17

nu

0.16

meg

0.16

Activations Density 0.025%

instances of the word "nu" and its variations, indicating a focus on terms related to nuanced or complex discussions

No Comments

No Known Activations