© 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 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. 29262
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with possession or belonging

    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
    umm
    -0.08
    OnClick
    -0.06
    atsu
    -0.06
    uga
    -0.06
    HF
    -0.06
     Sink
    -0.06
    Circular
    -0.06
     Wiring
    -0.06
     unreal
    -0.06
    ofilm
    -0.06
    POSITIVE LOGITS
    cke
    0.07
    onas
    0.07
    venes
    0.07
    омен
    0.07
    acon
    0.07
    ivol
    0.07
     Appearance
    0.07
    PasswordEncoder
    0.07
    овÑĸд
    0.06
    á»ijc
    0.06
    Activations Density 0.012%

    No Known Activations