© 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. 131000
    Prev
    Next
    INDEX
    Explanations

    possessive forms, particularly related to ownership 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
     itself
    -0.08
     Ãĸzel
    -0.08
    à¹Ģà¸Ńà¸ĩ
    -0.08
    raki
    -0.08
    OrNull
    -0.08
    airro
    -0.08
    ův
    -0.08
    ообÑĢаз
    -0.07
    ÙĦاÙĤ
    -0.07
    ë¿IJ
    -0.07
    POSITIVE LOGITS
     (
    0.08
     Jr
    0.06
    vert
    0.06
     apt
    0.06
    raquo
    0.06
    0.06
    948
    0.06
     (?)
    0.06
     ("
    0.06
    ÑĤим
    0.05
    Activations Density 0.038%

    No Known Activations