INDEX

Explanations

specific patterns and sequences in words, particularly character combinations and string anomalies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

á»Ł

-0.15

.removeListener

-0.15

empt

-0.15

 Bras

-0.15

adel

-0.15

nee

-0.14

iscal

-0.14

Î½Î¿Î¼

-0.13

/repos

-0.13

IDEO

-0.13

POSITIVE LOGITS

rs

0.38

0.35

0.34

ë¥´

0.33

×¨

0.32

'r

0.31

rcode

0.30

å°Ķ

0.30

ÑĢ

0.29

à¤°

0.28

Activations Density 0.116%

specific patterns and sequences in words, particularly character combinations and string anomalies

No Comments

No Known Activations