© 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. 79489
    Prev
    Next
    INDEX
    Explanations

    technical terms related to audio and communication devices

    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
    witch
    -0.07
    одо
    -0.06
     spice
    -0.06
    860
    -0.06
    psc
    -0.06
     WithEvents
    -0.06
    apon
    -0.06
    adoo
    -0.06
    idor
    -0.06
    ibold
    -0.06
    POSITIVE LOGITS
    pto
    0.08
     Invent
    0.07
    igh
    0.07
    achi
    0.06
    âĨij
    0.06
    _fg
    0.06
    ptom
    0.06
    hints
    0.06
    ering
    0.06
     Attorney
    0.06
    Activations Density 0.086%

    No Known Activations