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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57198
    Prev
    Next
    INDEX
    Explanations

    expressions related to possession or ownership

    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
     æĹ
    -0.07
    ÑĨеп
    -0.07
    724
    -0.07
     gridColumn
    -0.06
    Łèĥ½
    -0.06
     mour
    -0.06
     lately
    -0.06
    æĹ¢
    -0.06
    ÃĦ
    -0.06
    ulp
    -0.06
    POSITIVE LOGITS
    axe
    0.07
    ahoma
    0.06
    -inline
    0.06
     Alta
    0.06
    asma
    0.06
    inline
    0.06
    raquo
    0.06
     Hüs
    0.06
     myself
    0.06
    ,[],
    0.06
    Activations Density 0.000%

    No Known Activations