© 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. 69693
    Prev
    Next
    INDEX
    Explanations

    expressions related to quality and value judgments

    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
    stro
    -0.07
    oller
    -0.06
    orney
    -0.06
    PyObject
    -0.06
    .hu
    -0.06
    ivid
    -0.06
    irl
    -0.06
     neutral
    -0.06
    >Lorem
    -0.06
    iku
    -0.06
    POSITIVE LOGITS
     necessarily
    0.10
     demek
    0.07
    hea
    0.07
    umpt
    0.07
     jspb
    0.07
    ecessarily
    0.07
     ì¢ĭìĿĢ
    0.07
     superior
    0.06
     conse
    0.06
    upert
    0.06
    Activations Density 0.009%

    No Known Activations