© 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. 15-LLAMASCOPE-RES-131K
    11. 87746
    Prev
    Next
    INDEX
    Explanations

    quantifications and references to events or dates

    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
    esel
    -0.07
    orp
    -0.07
    iffin
    -0.07
    ÑĤаж
    -0.07
     lô
    -0.06
    ityEngine
    -0.06
    ewart
    -0.06
    ippo
    -0.06
    ebo
    -0.06
    atform
    -0.06
    POSITIVE LOGITS
    etooth
    0.06
     Mahm
    0.06
    PropertyValue
    0.06
    ĻĤ
    0.06
     Maul
    0.06
    inea
    0.05
    icator
    0.05
    _ATTRIBUTE
    0.05
     setattr
    0.05
    ButtonItem
    0.05
    Activations Density 0.001%

    No Known Activations