© 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. 124113
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptors related to positive evaluations or qualities

    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
    ÅĻiv
    -0.07
    sik
    -0.07
    esModule
    -0.07
    祥
    -0.06
    CALE
    -0.06
    .precision
    -0.06
     bout
    -0.06
    roupon
    -0.06
    ednou
    -0.06
    eon
    -0.06
    POSITIVE LOGITS
     simply
    0.07
    307
    0.06
    arg
    0.06
    iasco
    0.06
    neau
    0.06
     FALL
    0.06
    bery
    0.06
    276
    0.06
    nej
    0.06
    pany
    0.06
    Activations Density 0.050%

    No Known Activations