© 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. 58267
    Prev
    Next
    INDEX
    Explanations

    activities related to daily routines and personal interests

    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
    iscal
    -0.07
    _SAMPL
    -0.07
    insk
    -0.07
    rz
    -0.07
    .timeScale
    -0.07
     ÑĢаÑģпÑĢоÑģÑĤ
    -0.07
    ÃŃv
    -0.07
     ÑŁ
    -0.07
    rapper
    -0.07
    avr
    -0.07
    POSITIVE LOGITS
    åIJĦç§į
    0.08
     various
    0.07
     Various
    0.06
    Various
    0.06
     minute
    0.06
     оÑĩеÑĢед
    0.06
    595
    0.06
    licting
    0.05
     hopefully
    0.05
    UPPORTED
    0.05
    Activations Density 0.057%

    No Known Activations