© 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. 86295
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of belonging or connectedness

    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
    ault
    -0.07
    dep
    -0.07
    Lon
    -0.06
    perse
    -0.06
     consort
    -0.06
     counted
    -0.06
    #ac
    -0.06
    isko
    -0.06
    lon
    -0.06
    'icon
    -0.06
    POSITIVE LOGITS
     urgency
    0.07
    ahat
    0.07
     entitlement
    0.07
    liness
    0.07
     Ent
    0.07
    illes
    0.07
     být
    0.07
     ownership
    0.07
    oss
    0.07
    ovich
    0.06
    Activations Density 0.017%

    No Known Activations