© 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 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. 78431
    Prev
    Next
    INDEX
    Explanations

    various forms of storytelling that involve complex character dynamics and moral issues

    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
    omen
    -0.07
    opsy
    -0.06
    âĩ
    -0.06
    że
    -0.06
    upply
    -0.06
    tual
    -0.06
    μει
    -0.06
    opup
    -0.06
    bsolute
    -0.06
    otten
    -0.06
    POSITIVE LOGITS
     ur
    0.06
     Bj
    0.06
    áš
    0.06
     Ur
    0.06
     upside
    0.06
    ÂŃn
    0.06
    retval
    0.06
    ows
    0.06
    .liferay
    0.06
    Nullable
    0.06
    Activations Density 0.158%

    No Known Activations