© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 71979
    Prev
    Next
    INDEX
    Explanations

    references to various religious or spiritual identities

    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
    .scalablytyped
    -0.08
    awan
    -0.07
    weis
    -0.07
    ckill
    -0.06
    ramer
    -0.06
     WARRANT
    -0.06
    ores
    -0.06
    ailable
    -0.06
    ayer
    -0.06
    ús
    -0.06
    POSITIVE LOGITS
     about
    0.07
    libc
    0.07
    еж
    0.07
    itone
    0.07
    about
    0.06
     constituents
    0.06
     regarding
    0.06
    ÑĢÑĸÑĩ
    0.06
     asking
    0.06
    want
    0.06
    Activations Density 0.019%

    No Known Activations