© 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. 79421
    Prev
    Next
    INDEX
    Explanations

    references to user-related settings 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
    azio
    -0.06
    ksen
    -0.06
     Kr
    -0.06
    umbo
    -0.06
    /facebook
    -0.06
    agon
    -0.06
    leo
    -0.06
    epam
    -0.06
    asar
    -0.06
     Mill
    -0.06
    POSITIVE LOGITS
    ç½
    0.07
    ì§Ģë§ī
    0.06
    -grade
    0.06
    782
    0.06
    ãĥ¼ãĥł
    0.06
    crit
    0.06
    åĢ
    0.06
    amework
    0.06
     Weber
    0.06
    larıyla
    0.06
    Activations Density 0.002%

    No Known Activations