© 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. 17-LLAMASCOPE-RES-131K
    11. 86819
    Prev
    Next
    INDEX
    Explanations

    specific phone number formatting and validation criteria

    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
    etros
    -0.07
    gesi
    -0.07
    -loader
    -0.07
    #ga
    -0.06
     kê
    -0.06
    ogenous
    -0.06
     initials
    -0.06
    ronic
    -0.06
    /loading
    -0.06
    _IMP
    -0.06
    POSITIVE LOGITS
     phone
    0.16
     Phone
    0.15
     telephone
    0.14
    phone
    0.13
     phones
    0.13
    çĶµè¯Ŀ
    0.13
    -phone
    0.13
     PHONE
    0.12
    Phone
    0.12
    _phone
    0.12
    Activations Density 0.010%

    No Known Activations