© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4303
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and functionalities of software or systems

    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
    OffsetTable
    -0.08
    meli
    -0.08
    _CHARS
    -0.07
    UTERS
    -0.07
    jspx
    -0.07
    .nlm
    -0.07
     nackte
    -0.07
    âĢ¦"↵↵
    -0.07
    usercontent
    -0.07
     (č↵
    -0.07
    POSITIVE LOGITS
    .Guna
    0.07
    .bunifuFlatButton
    0.07
    ÑĢÑıдÑĥ
    0.06
    -backend
    0.06
    ovable
    0.06
    ToPoint
    0.05
    /includes
    0.05
    Geometry
    0.05
    0.05
    .timeScale
    0.05
    Activations Density 0.686%

    No Known Activations