© 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. 17-LLAMASCOPE-RES-131K
    11. 29431
    Prev
    Next
    INDEX
    Explanations

    phrases that convey a moral or religious stance

    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
     Stuff
    -0.09
    _stuff
    -0.08
     stuff
    -0.08
    arih
    -0.07
    rego
    -0.07
     Cla
    -0.07
     ÑģоÑģ
    -0.07
    iddi
    -0.07
    óst
    -0.07
    THING
    -0.07
    POSITIVE LOGITS
     jak
    0.06
     unto
    0.06
    .executeQuery
    0.06
     dile
    0.06
    ulo
    0.06
    à¹ĥà¸Ķ
    0.06
    cia
    0.06
     tanto
    0.06
    phia
    0.05
     há»ĵ
    0.05
    Activations Density 0.000%

    No Known Activations