© 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. 75042
    Prev
    Next
    INDEX
    Explanations

    inquiries related to the firm's services and operations

    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
     perhaps
    -0.06
    acro
    -0.06
    736
    -0.06
    aments
    -0.06
    ament
    -0.06
     maybe
    -0.06
    orsch
    -0.06
    неÑĢ
    -0.06
    vid
    -0.06
    iton
    -0.06
    POSITIVE LOGITS
    ³
    0.07
    ëĤĺìļĶ
    0.06
    DataURL
    0.06
    APTER
    0.06
    BT
    0.06
    uyu
    0.06
    igar
    0.06
     puedo
    0.06
    PointerException
    0.06
    alty
    0.06
    Activations Density 0.011%

    No Known Activations