© 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. 54339
    Prev
    Next
    INDEX
    Explanations

    references to political races and reforms

    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
    rias
    -0.09
    дап
    -0.07
    MediaType
    -0.07
    attern
    -0.07
    assed
    -0.07
    ÑĢд
    -0.07
    rnÄĽ
    -0.07
    pgsql
    -0.07
    .sourceforge
    -0.07
    umbing
    -0.07
    POSITIVE LOGITS
    iola
    0.06
     Ging
    0.06
    115
    0.06
    สม
    0.06
    796
    0.06
     partly
    0.06
     Ches
    0.05
    _PROC
    0.05
    UDA
    0.05
    we
    0.05
    Activations Density 0.000%

    No Known Activations