© 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. 2782
    Prev
    Next
    INDEX
    Explanations

    references to people and their roles in legal or criminal 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
    avras
    -0.07
     اÙĦرسÙħ
    -0.07
    aston
    -0.07
    ÏĦÏĮ
    -0.06
    .IContainer
    -0.06
    ograd
    -0.06
    CanBe
    -0.06
    rega
    -0.06
     coin
    -0.06
    blink
    -0.06
    POSITIVE LOGITS
    woke
    0.06
    Spot
    0.06
    uffer
    0.06
     had
    0.06
    669
    0.06
     SSR
    0.06
     spot
    0.06
    ãģ¾ãģļ
    0.06
     initially
    0.06
    arkin
    0.06
    Activations Density 0.036%

    No Known Activations