© 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. 9-LLAMASCOPE-RES-131K
    11. 97500
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to educational and community-oriented programs

    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
     pylint
    -0.08
     diversion
    -0.06
    edla
    -0.06
    ÃŃrk
    -0.06
     rowspan
    -0.06
    fillType
    -0.06
    :UIAlert
    -0.06
    letcher
    -0.06
    HTTPRequest
    -0.06
    (strcmp
    -0.06
    POSITIVE LOGITS
    олÑİ
    0.07
     Mandal
    0.07
     Cannon
    0.07
    åŃIJãģ¯
    0.06
    errat
    0.06
    campo
    0.06
    ilver
    0.06
    .library
    0.06
    abay
    0.06
    357
    0.06
    Activations Density 0.034%

    No Known Activations