© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 61378
    Prev
    Next
    INDEX
    Explanations

    references to personal identity and self-deprecation

    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
    mdir
    -0.07
    alue
    -0.06
    ocop
    -0.06
    edik
    -0.06
    asta
    -0.06
    ielding
    -0.06
    lahoma
    -0.06
    ough
    -0.06
    agina
    -0.06
    веÑģÑĤ
    -0.06
    POSITIVE LOGITS
     myself
    0.08
    à¤łà¤¨
    0.07
     Shuttle
    0.07
     meth
    0.07
    morph
    0.06
    ARSE
    0.06
     shuttle
    0.06
     morph
    0.06
     moi
    0.06
    ادات
    0.06
    Activations Density 0.020%

    No Known Activations