© 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. 9-LLAMASCOPE-RES-131K
    11. 98504
    Prev
    Next
    INDEX
    Explanations

    terms associated with social issues and ethical dilemmas

    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
    iec
    -0.07
    ami
    -0.06
    ãĥ»ãĥ»ãĥ»↵↵
    -0.06
    wert
    -0.06
    ови
    -0.06
    caf
    -0.06
    ful
    -0.06
    ãĥĥ
    -0.06
    ÑĢе
    -0.06
    arser
    -0.06
    POSITIVE LOGITS
    ediator
    0.07
    conde
    0.07
    undra
    0.07
    nesia
    0.07
    352
    0.06
    ulance
    0.06
    à¹ģละà¸ģาร
    0.06
    planation
    0.06
    esda
    0.06
    ecut
    0.06
    Activations Density 0.077%

    No Known Activations