© 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. 29131
    Prev
    Next
    INDEX
    Explanations

    references to the sky and its various descriptions

    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
    رش
    -0.07
    ombre
    -0.07
    InSection
    -0.07
    hip
    -0.07
    oling
    -0.07
     пÑĢиб
    -0.07
     Giang
    -0.07
     вп
    -0.07
    anio
    -0.06
     ÙħکاÙĨÛĮ
    -0.06
    POSITIVE LOGITS
    /cloud
    0.08
    borne
    0.07
    ic
    0.07
     skies
    0.07
    and
    0.06
    walk
    0.06
    IDGET
    0.06
     trá»Ŀi
    0.06
     roof
    0.06
    roof
    0.06
    Activations Density 0.007%

    No Known Activations