© 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. 61840
    Prev
    Next
    INDEX
    Explanations

    structured numerical data, particularly in the context of educational institutions

    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
    (æ°´
    -0.08
    _handling
    -0.08
    irsch
    -0.07
    ermo
    -0.07
    vanished
    -0.07
     desar
    -0.07
    침
    -0.07
    _installed
    -0.07
    Occurred
    -0.07
    iminal
    -0.07
    POSITIVE LOGITS
    epad
    0.06
    sock
    0.06
     Franc
    0.06
    ubbo
    0.06
    673
    0.06
     Grey
    0.06
    uegos
    0.06
    bsites
    0.06
     пов
    0.05
    refixer
    0.05
    Activations Density 0.001%

    No Known Activations