© 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. 9-LLAMASCOPE-RES-131K
    11. 96932
    Prev
    Next
    INDEX
    Explanations

    references to religious or spiritual concepts, particularly in a textual context

    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
     bul
    -0.07
    rie
    -0.06
    nea
    -0.06
    appings
    -0.06
    Ctl
    -0.06
    quete
    -0.06
    ÑĮв
    -0.06
     Talking
    -0.06
    ents
    -0.06
    ONA
    -0.05
    POSITIVE LOGITS
    urate
    0.07
     Toastr
    0.07
    olik
    0.07
    andler
    0.07
    -floating
    0.07
    zym
    0.06
    à¹īà¸ĩ
    0.06
    áj
    0.06
    owell
    0.06
    082
    0.06
    Activations Density 0.011%

    No Known Activations