INDEX

Explanations

references to data metrics and financial assessments

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

åŃ¤

-0.17

/fw

-0.16

inkel

-0.16

æīĢæľī

-0.16

å¤ļ

-0.15

onz

-0.15

Ð¾ÑģÑĤÐ°ÑĤ

-0.15

olib

-0.14

 Pond

-0.14

urst

-0.14

POSITIVE LOGITS

 devoted

0.27

 dedicated

0.19

 Ð¿ÑĢÐ¸ÑħÐ¾Ð´

0.18

 consists

0.18

 consisted

0.17

endra

0.16

ammen

0.16

 covered

0.15

 Dedicated

0.15

 consisting

0.15

Activations Density 0.234%

references to data metrics and financial assessments

No Comments

No Known Activations