© 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. 55192
    Prev
    Next
    INDEX
    Explanations

    entities and roles within professional organizations and leadership positions

    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
     å®
    -0.07
    buz
    -0.07
    ạng
    -0.06
    íĿ¬
    -0.06
    zes
    -0.06
    iaux
    -0.06
    asm
    -0.06
    entin
    -0.06
    lech
    -0.06
    æ³½
    -0.06
    POSITIVE LOGITS
    /or
    0.08
    ród
    0.06
    onso
    0.06
    incinn
    0.06
     frequent
    0.06
    atro
    0.06
    inta
    0.06
    yro
    0.06
    tempts
    0.06
    osite
    0.06
    Activations Density 0.011%

    No Known Activations