© 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. 120413
    Prev
    Next
    INDEX
    Explanations

    references to professional organizations and real estate appraisal topics

    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
    Ńå·ŀ
    -0.07
    ieves
    -0.06
    frey
    -0.06
    Ìģ
    -0.06
    862
    -0.06
    aska
    -0.06
    _mesh
    -0.06
    ahkan
    -0.06
    ibbon
    -0.06
    âce
    -0.06
    POSITIVE LOGITS
     subdivisions
    0.06
     Val
    0.06
     Improvement
    0.06
    vell
    0.06
    TRS
    0.06
    illard
    0.06
    sko
    0.06
    istence
    0.06
    stad
    0.06
     appel
    0.06
    Activations Density 0.001%

    No Known Activations