© 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. 105354
    Prev
    Next
    INDEX
    Explanations

    specific numeric values or counts related to various topics or contexts

    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
    hv
    -0.07
     kø
    -0.07
    azon
    -0.07
    CREMENT
    -0.06
    jt
    -0.06
    èª
    -0.06
    æŀ
    -0.06
    inv
    -0.06
    deo
    -0.06
    ena
    -0.06
    POSITIVE LOGITS
     final
    0.08
    bonus
    0.08
     bonus
    0.08
     Bonus
    0.07
    artin
    0.07
    eper
    0.07
    ackbar
    0.07
     Final
    0.07
    getMock
    0.06
    Bonus
    0.06
    Activations Density 0.003%

    No Known Activations