© 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. 4591
    Prev
    Next
    INDEX
    Explanations

    phrases that express identity and self-acceptance

    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
    OLA
    -0.08
    że
    -0.07
    cak
    -0.07
    غات
    -0.07
    Ø«
    -0.07
    ิà¸Ī
    -0.06
    ibile
    -0.06
    heed
    -0.06
    است
    -0.06
    DataProvider
    -0.06
    POSITIVE LOGITS
     either
    0.06
     somebody
    0.06
    æµħ
    0.06
     a
    0.06
     gì
    0.06
     _____
    0.06
    wi
    0.06
     royalty
    0.06
    atrix
    0.06
     someone
    0.06
    Activations Density 0.048%

    No Known Activations