© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 119679
    Prev
    Next
    INDEX
    Explanations

    phrases or sections of text related to licensing or legal specifications

    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
    adge
    -0.07
    emme
    -0.07
    emmel
    -0.07
     ill
    -0.06
    ÅĻiv
    -0.06
    endir
    -0.06
    umlah
    -0.06
    اخت
    -0.06
    ocode
    -0.06
     cathedral
    -0.06
    POSITIVE LOGITS
     sweat
    0.08
     Sweat
    0.07
    cock
    0.07
    ITLE
    0.07
    ÑĥÑĩа
    0.06
    ondo
    0.06
    693
    0.06
    832
    0.06
    376
    0.06
    :host
    0.06
    Activations Density 0.001%

    No Known Activations