© 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. 70277
    Prev
    Next
    INDEX
    Explanations

    the structure of phrases and clauses involving "of," particularly in the context of lists or categories

    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
    quier
    -0.08
    enders
    -0.08
    anel
    -0.08
    iras
    -0.08
    idente
    -0.08
    лÑİ
    -0.08
    ductor
    -0.08
    ChangedEventArgs
    -0.08
    arend
    -0.08
    ovah
    -0.08
    POSITIVE LOGITS
     teams
    0.07
    ,
    0.06
     securely
    0.06
     committees
    0.06
     leveling
    0.06
    959
    0.05
     merry
    0.05
    enz
    0.05
    ele
    0.05
    us
    0.05
    Activations Density 0.032%

    No Known Activations