© 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. 92156
    Prev
    Next
    INDEX
    Explanations

    references to professional qualifications and expertise

    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
     зави
    -0.09
    laus
    -0.08
    kud
    -0.08
    idor
    -0.08
    GRES
    -0.08
    ensa
    -0.08
     огÑĢа
    -0.07
    edor
    -0.07
    afen
    -0.07
     диви
    -0.07
    POSITIVE LOGITS
     selected
    0.08
     chosen
    0.08
     who
    0.07
     helm
    0.07
     available
    0.06
     team
    0.06
    who
    0.06
     avail
    0.06
     trans
    0.06
    mie
    0.06
    Activations Density 0.026%

    No Known Activations