© 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. 9-LLAMASCOPE-RES-131K
    11. 96807
    Prev
    Next
    INDEX
    Explanations

    terms related to protection and rights, especially in legal or social contexts

    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
    пÑĢимеÑĢ
    -0.08
    enza
    -0.07
    ilib
    -0.07
     Rip
    -0.07
    idges
    -0.06
    etak
    -0.06
    ipay
    -0.06
    /DD
    -0.06
    enek
    -0.06
    usalem
    -0.06
    POSITIVE LOGITS
    ť
    0.08
    _qos
    0.07
    -duty
    0.06
    Ïī
    0.06
    .getStatusCode
    0.06
    à¸ĵà¸ij
    0.06
     BÃŃ
    0.06
    eydi
    0.06
     undef
    0.06
     stump
    0.06
    Activations Density 0.001%

    No Known Activations