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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73780
    Prev
    Next
    INDEX
    Explanations

    references to deep emotional connections or relationships

    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
     cad
    -0.06
     Mot
    -0.06
     "
    -0.06
    EAR
    -0.06
    ÑĢÑĥ
    -0.06
    PageIndex
    -0.06
     fisse
    -0.06
     Shib
    -0.06
    .Suppress
    -0.06
    _nat
    -0.06
    POSITIVE LOGITS
    iom
    0.07
     informations
    0.07
     Laud
    0.06
    atile
    0.06
    ENCHMARK
    0.06
    TOTYPE
    0.06
    lobal
    0.06
    иденÑĤ
    0.06
    gren
    0.06
    dıģında
    0.06
    Activations Density 0.000%

    No Known Activations