© 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. 58121
    Prev
    Next
    INDEX
    Explanations

    common correlating phrases and verb forms that represent actions or states

    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
    ĢìĿ´
    -0.07
    ullo
    -0.07
    eln
    -0.07
    illance
    -0.07
    inesis
    -0.06
    krom
    -0.06
    porter
    -0.06
    positor
    -0.06
    aska
    -0.06
    otte
    -0.06
    POSITIVE LOGITS
    CJK
    0.07
    abouts
    0.07
    ÑĩаÑģÑĤ
    0.07
    agit
    0.07
    ãģŁãģĦ
    0.07
    urry
    0.06
    DSA
    0.06
    EDA
    0.06
    Sensitive
    0.06
    gın
    0.06
    Activations Density 0.001%

    No Known Activations