© 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. 69845
    Prev
    Next
    INDEX
    Explanations

    concepts related to moral and natural law

    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
     addCriterion
    -0.07
     bols
    -0.07
     migrationBuilder
    -0.07
    аÑĢÑĩ
    -0.07
    codegen
    -0.07
    _exc
    -0.07
    sembl
    -0.07
    oki
    -0.07
    RefPtr
    -0.07
    ordinator
    -0.07
    POSITIVE LOGITS
     conscience
    0.10
     natural
    0.09
     Natural
    0.07
     nett
    0.06
    natural
    0.06
    Natural
    0.06
     reflective
    0.06
     Natur
    0.06
     object
    0.06
     Reason
    0.06
    Activations Density 0.010%

    No Known Activations