© 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. 104513
    Prev
    Next
    INDEX
    Explanations

    evaluative expressions related to performance or quality

    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
     Spiral
    -0.07
    ambre
    -0.07
     Daniels
    -0.06
    accion
    -0.06
    abee
    -0.06
    _TS
    -0.06
    .EventQueue
    -0.06
    身ä¸Ĭ
    -0.06
     Hòa
    -0.06
    647
    -0.06
    POSITIVE LOGITS
     underst
    0.13
     redund
    0.07
    ednou
    0.07
     redundancy
    0.07
     say
    0.06
    regor
    0.06
     unders
    0.06
    yal
    0.06
    ãĥ¼ãĥ«
    0.06
     Inf
    0.06
    Activations Density 0.004%

    No Known Activations