© 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. 86371
    Prev
    Next
    INDEX
    Explanations

    terms related to restrictions or prohibitions

    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
    ptime
    -0.07
    isans
    -0.07
    chia
    -0.07
    leh
    -0.07
    enz
    -0.07
    olicit
    -0.07
    ying
    -0.07
    VD
    -0.07
    ³
    -0.07
    yal
    -0.07
    POSITIVE LOGITS
    aires
    0.07
     acces
    0.06
     access
    0.06
     Crom
    0.06
    ovny
    0.06
     us
    0.06
    ISTER
    0.06
    ister
    0.06
     ÑģобÑĸ
    0.06
    ariat
    0.06
    Activations Density 0.014%

    No Known Activations