INDEX

Explanations

references to educational practices and strategies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

OutOfBounds

-0.16

ebb

-0.15

ceb

-0.15

assic

-0.15

arend

-0.14

uda

-0.14

 DBNull

-0.14

cee

-0.14

/site

-0.14

ãĤ¤ãĥī

-0.13

POSITIVE LOGITS

ets

0.17

YZ

0.16

adol

0.15

 Dixon

0.15

artz

0.14

agrams

0.14

DOC

0.14

0.13

 interrupt

0.13

BY

0.13

Activations Density 0.097%

references to educational practices and strategies

No Comments

No Known Activations