© 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. 9-LLAMASCOPE-RES-131K
    11. 94942
    Prev
    Next
    INDEX
    Explanations

    items or activities related to trading and sales

    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
    rella
    -0.07
     options
    -0.07
     Od
    -0.06
    readcr
    -0.06
    ickerView
    -0.06
    áºł
    -0.06
    '=>['
    -0.06
    ADB
    -0.06
    WEEN
    -0.06
    apore
    -0.06
    POSITIVE LOGITS
     ë°
    0.07
    eldon
    0.07
    sat
    0.06
     Jarvis
    0.06
    /repos
    0.06
    erral
    0.06
    leftright
    0.06
    ë°
    0.06
     ÑģÑĥÑĤ
    0.06
    âr
    0.06
    Activations Density 0.000%

    No Known Activations