INDEX

Explanations

references to educational achievements and graduations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 Preis

-0.17

/of

-0.17

fried

-0.15

egration

-0.15

onn

-0.15

_gradient

-0.14

erville

-0.14

ãĥªãĤ«

-0.14

_gradients

-0.14

.gradient

-0.14

POSITIVE LOGITS

cum

0.24

Cum

0.23

sum

0.23

 magna

0.22

 suma

0.21

 Magn

0.20

Cum

0.19

Sum

0.18

-sum

0.17

uated

0.17

Activations Density 0.015%

references to educational achievements and graduations

No Comments

No Known Activations