© 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. 61951
    Prev
    Next
    INDEX
    Explanations

    words related to the structure and organization of text or code

    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
    ateria
    -0.07
    seniz
    -0.07
    clc
    -0.07
     впол
    -0.07
    meli
    -0.07
    erken
    -0.07
    eyJ
    -0.07
    íı
    -0.06
    ķìĿ¸
    -0.06
    ATIO
    -0.06
    POSITIVE LOGITS
     Griffith
    0.07
    dol
    0.06
    _ALIGNMENT
    0.05
     Dam
    0.05
    isma
    0.05
    _ALIGN
    0.05
    ãĤ´
    0.05
    ÑĢоÑģ
    0.05
     Alma
    0.05
    転
    0.05
    Activations Density 0.001%

    No Known Activations