INDEX

Explanations

multiple occurrences of the word "and."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 viá»ĩc

-0.15

iendo

-0.14

ï¸

-0.14

uts

-0.13

NSObject

-0.13

Teh

-0.13

urlencode

-0.13

ing

-0.13

uje

-0.13

>this

-0.13

POSITIVE LOGITS

 generally

0.19

ecies

0.17

 thereby

0.17

essim

0.16

 Generally

0.16

ICO

0.16

 other

0.15

/or

0.15

usercontent

0.14

apore

0.14

Activations Density 0.275%

multiple occurrences of the word "and."

No Comments

No Known Activations