© 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. 29462
    Prev
    Next
    INDEX
    Explanations

    phrases asserting the concept of rights and entitlements

    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
    otos
    -0.07
    ona
    -0.07
    uria
    -0.06
    _goto
    -0.06
    oks
    -0.06
    oto
    -0.06
    .infinity
    -0.06
    aire
    -0.06
    endencies
    -0.06
     Crowley
    -0.06
    POSITIVE LOGITS
    ahlen
    0.08
     Pell
    0.07
    ivet
    0.07
    _SKIP
    0.07
    GetObject
    0.07
    ephy
    0.06
    aty
    0.06
     Demand
    0.06
    expect
    0.06
    -demand
    0.06
    Activations Density 0.009%

    No Known Activations