INDEX

Explanations

statistical terms and concepts related to research methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ãĥ³ãĥĨãĤ£

-0.17

<$

-0.16

 predicting

-0.15

 probabil

-0.15

 predicts

-0.14

APPING

-0.14

bol

-0.14

ire

-0.14

pageTitle

-0.14

emann

-0.14

POSITIVE LOGITS

 censor

0.20

iid

0.20

 miss

0.19

 Wald

0.18

Ney

0.17

 ident

0.16

 shrink

0.16

 fitted

0.16

 Bootstrap

0.16

 Penal

0.16

Activations Density 0.086%

statistical terms and concepts related to research methodologies

No Comments

No Known Activations