INDEX

Explanations

references to licenses and legal terms related to software

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ruz

-0.16

ieber

-0.16

yi

-0.15

erial

-0.15

olare

-0.15

 recurse

-0.14

adero

-0.14

dsn

-0.14

Ø®

-0.14

olate

-0.14

POSITIVE LOGITS

0.16

ForKey

0.15

/LICENSE

0.15

Ð½Ð¸Ð½

0.15

 bahis

0.14

æĳ©

0.14

Mit

0.13

 DISCLAIM

0.13

Activations Density 0.005%

references to licenses and legal terms related to software

No Comments

No Known Activations