© 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. 79745
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating support, reliability, and assurance

    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
    ossa
    -0.07
    ChangeEvent
    -0.06
    eldon
    -0.06
    acic
    -0.06
    rk
    -0.06
     Braun
    -0.06
    celed
    -0.06
     ant
    -0.06
     Richard
    -0.06
    isha
    -0.06
    POSITIVE LOGITS
     backs
    0.09
     backing
    0.09
     Covered
    0.09
     covered
    0.09
    covered
    0.08
    -cover
    0.08
    backs
    0.08
     COVER
    0.07
    ë°±
    0.07
    andler
    0.07
    Activations Density 0.029%

    No Known Activations