© 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. 94666
    Prev
    Next
    INDEX
    Explanations

    terms related to historical or ceremonial practices

    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
     Irma
    -0.07
    ammo
    -0.07
    allet
    -0.07
    æ¹
    -0.06
    acht
    -0.06
    ab
    -0.06
    abr
    -0.05
    494
    -0.05
    Ø´ÛĮ
    -0.05
    amm
    -0.05
    POSITIVE LOGITS
    odb
    0.08
    .Guna
    0.08
    etting
    0.07
    okud
    0.07
    dana
    0.07
    omap
    0.07
    _fb
    0.07
    ERCHANT
    0.07
    _$_
    0.07
    osto
    0.07
    Activations Density 0.001%

    No Known Activations