INDEX

Explanations

numbers related to data and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

stad

-0.15

Ð°Ð»Ð¾Ð²

-0.15

rael

-0.14

ucu

-0.14

ovali

-0.14

roids

-0.13

ric

-0.13

null

-0.13

ultipart

-0.13

********************************************************************************

-0.13

POSITIVE LOGITS

nd

0.29

-thirds

0.24

 dozen

0.20

gether

0.17

ï¸ı

0.16

antan

0.16

/th

0.15

CLR

0.14

 thirds

0.14

 otherwise

0.14

Activations Density 0.184%

numbers related to data and statistics

No Comments

No Known Activations