© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15703
    Prev
    Next
    INDEX
    Explanations

    concepts related to property rights and political-economic structures

    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
    ãĥ¼ãĤ¸
    -0.07
    obl
    -0.07
    ulan
    -0.07
    ulong
    -0.07
    ÑĤÑĮ
    -0.06
    âͬ
    -0.06
    irie
    -0.06
    à¤¿à¤Ľ
    -0.06
    ìĪ
    -0.06
     اسÙĦاÙħ
    -0.06
    POSITIVE LOGITS
     peaceful
    0.07
     consent
    0.07
     åĶ
    0.07
     trespass
    0.07
     peacefully
    0.07
    isches
    0.07
     Stateless
    0.06
     Straw
    0.06
     Libertarian
    0.06
     Graz
    0.06
    Activations Density 0.016%

    No Known Activations