© 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. 86823
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities and their consequences

    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
    ÑĢеж
    -0.07
    ["$
    -0.07
    eria
    -0.07
     kin
    -0.07
    Segue
    -0.06
    одо
    -0.06
     Kin
    -0.06
    ully
    -0.06
    ibal
    -0.06
    astes
    -0.06
    POSITIVE LOGITS
     preca
    0.07
    vable
    0.06
    immers
    0.06
    ên
    0.06
    ernet
    0.06
     charged
    0.06
    енка
    0.06
    osome
    0.06
     transcript
    0.06
    êm
    0.06
    Activations Density 0.001%

    No Known Activations