© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84629
    Prev
    Next
    INDEX
    Explanations

    possessive forms and attributes related to ownership or instances reflective of possession

    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
    arası
    -0.06
    .latest
    -0.06
     Canter
    -0.06
    ids
    -0.06
     company
    -0.06
     ones
    -0.06
    наÑĢ
    -0.06
    imo
    -0.06
    _projects
    -0.06
    изнеÑģ
    -0.06
    POSITIVE LOGITS
     contents
    0.08
    olutely
    0.07
    主人
    0.07
    Accessibility
    0.07
    contents
    0.07
    ora
    0.06
     subtitle
    0.06
    VIC
    0.06
    oks
    0.06
    leDb
    0.06
    Activations Density 0.021%

    No Known Activations