© 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. 27318
    Prev
    Next
    INDEX
    Explanations

    discussions around the separation of church and state in the context of education policies

    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
    ÙĩÙĨ
    -0.07
    ilon
    -0.06
    'gc
    -0.06
    emu
    -0.06
     sigma
    -0.06
    anders
    -0.06
     Schema
    -0.06
    ColumnType
    -0.06
     Loc
    -0.06
     Sig
    -0.06
    POSITIVE LOGITS
     public
    0.07
     PUBLIC
    0.07
     Public
    0.07
    -public
    0.07
     neutral
    0.07
     Bradford
    0.07
    /public
    0.07
    neutral
    0.06
     pros
    0.06
     neutrality
    0.06
    Activations Density 0.025%

    No Known Activations