© 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. 17-LLAMASCOPE-RES-131K
    11. 87971
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related terms indicating ownership or personal connection

    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
    AMESPACE
    -0.08
    kem
    -0.07
    orro
    -0.07
    aroo
    -0.07
    еÑĢп
    -0.07
    оÑĢм
    -0.07
    ãĥ¼ãĥŀ
    -0.07
    ãĢħ
    -0.07
    zin
    -0.06
    жд
    -0.06
    POSITIVE LOGITS
    sel
    0.07
     Sel
    0.06
    ippi
    0.06
    egin
    0.06
    SELF
    0.06
    uet
    0.06
    ×ķ
    0.06
    self
    0.06
    acher
    0.06
     luck
    0.06
    Activations Density 0.003%

    No Known Activations