© 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 EvalsExportsAPI 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. 106142
    Prev
    Next
    INDEX
    Explanations

    words indicating amounts or quantities

    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
    çı
    -0.07
    ubi
    -0.07
    pn
    -0.06
    adors
    -0.06
    EEK
    -0.06
    _Session
    -0.06
    cling
    -0.06
    íĥķ
    -0.06
    cie
    -0.06
    ÙĤدر
    -0.06
    POSITIVE LOGITS
    avior
    0.07
    ÑĢÑĥг
    0.07
    ancock
    0.06
    endar
    0.06
    tual
    0.06
    utral
    0.06
    otal
    0.06
    zy
    0.06
    dy
    0.06
    yt
    0.06
    Activations Density 0.000%

    No Known Activations