© 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. 128170
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and settlement negotiations

    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
    ulen
    -0.07
    decltype
    -0.07
    usercontent
    -0.07
    quier
    -0.06
    _markup
    -0.06
    eyen
    -0.06
    otte
    -0.06
    stery
    -0.06
    anke
    -0.06
    ë³µ
    -0.06
    POSITIVE LOGITS
    endar
    0.07
     yourselves
    0.07
    .layout
    0.07
    agan
    0.06
     ÑĢам
    0.06
    argon
    0.06
    两人
    0.06
     unsupported
    0.06
     agreeing
    0.06
     Wrath
    0.06
    Activations Density 0.003%

    No Known Activations