© 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. 79382
    Prev
    Next
    INDEX
    Explanations

    references to local community events and organizations, particularly those involving women

    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
    eru
    -0.07
    æ²ĸ
    -0.07
    onas
    -0.07
    Outline
    -0.07
    ãĥ³ãĥĶ
    -0.07
    Äįit
    -0.06
    .NaN
    -0.06
    MediaType
    -0.06
    ÑĨе
    -0.06
    urette
    -0.06
    POSITIVE LOGITS
     women
    0.07
     Women
    0.07
    women
    0.06
     lun
    0.06
     men
    0.06
     city
    0.06
     dut
    0.06
     Pinterest
    0.06
     civic
    0.06
    婦
    0.06
    Activations Density 0.002%

    No Known Activations