© 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 EvalsExportsinterp-engineNEWAPI 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. 80187
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    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
    pler
    -0.07
    //{{
    -0.07
    ÙĥÙĨ
    -0.06
    ali
    -0.06
    ni
    -0.06
    eni
    -0.06
    _GF
    -0.06
     luder
    -0.06
     nuest
    -0.06
    -properties
    -0.06
    POSITIVE LOGITS
     entire
    0.08
    缮
    0.08
    'e
    0.07
     aim
    0.07
     goal
    0.07
     whole
    0.07
    ’e
    0.07
     problem
    0.06
     MetroFramework
    0.06
     cÃłng
    0.06
    Activations Density 0.017%

    No Known Activations