INDEX

Explanations

references to frequency and quantity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

itecture

-0.16

rogram

-0.15

à¸£à¸¡

-0.15

ÑĤÐ°Ð¶

-0.15

ucer

-0.14

lain

-0.14

adan

-0.14

clud

-0.14

upil

-0.14

iverse

-0.13

POSITIVE LOGITS

 modern

0.27

modern

0.21

 times

0.20

 ÑģÐ¾Ð²ÑĢÐµÐ¼

0.20

 people

0.20

 commercially

0.19

rei

0.18

 contemporary

0.17

 successful

0.17

 ÑģÑĥÑĩÐ°Ñģ

0.17

Activations Density 0.161%

references to frequency and quantity

No Comments

No Known Activations