© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27536
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to data states or statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otton
    -0.07
    vsp
    -0.07
    GINE
    -0.07
    bum
    -0.07
    antity
    -0.07
    _whitespace
    -0.07
    PostalCodes
    -0.07
    $',
    -0.07
    aret
    -0.07
    byss
    -0.07
    POSITIVE LOGITS
    ×Ļ
    0.06
     prime
    0.06
    ETERS
    0.05
     intric
    0.05
    rol
    0.05
    خت
    0.05
    ÅĤu
    0.05
    ´Ī
    0.05
    _
    0.05
    ¦
    0.05
    Activations Density 0.003%

    No Known Activations