© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 121311
    Prev
    Next
    INDEX
    Explanations

    terms related to legal restrictions and prohibitions

    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
    eric
    -0.08
    fak
    -0.07
    Vir
    -0.07
    ÑģÑĤÑĢÑĥ
    -0.07
    ghan
    -0.07
    зв
    -0.07
    heim
    -0.07
    _sid
    -0.06
    çģ
    -0.06
    ouro
    -0.06
    POSITIVE LOGITS
     contact
    0.09
    /contact
    0.08
     contacto
    0.07
     contacts
    0.07
    contact
    0.07
    voir
    0.07
    -contact
    0.07
    contacts
    0.06
     contacting
    0.06
    ysz
    0.06
    Activations Density 0.003%

    No Known Activations