© 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. 3452
    Prev
    Next
    INDEX
    Explanations

    elements of artistic or abstract installations and sculptures

    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
     Superv
    -0.06
     asset
    -0.06
    187
    -0.06
     superv
    -0.06
     Candle
    -0.06
    jah
    -0.06
     error
    -0.06
    -
    -0.06
    asset
    -0.06
    257
    -0.06
    POSITIVE LOGITS
    ̣
    0.08
    âĺħâĺħ
    0.08
    achat
    0.07
    installation
    0.07
    ÌĨ
    0.07
    _hooks
    0.07
    uspended
    0.07
    ↵↵
    0.07
    Installation
    0.07
     suspended
    0.07
    Activations Density 0.022%

    No Known Activations