© 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. 127078
    Prev
    Next
    INDEX
    Explanations

    HTML form elements and their attributes

    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
    isas
    -0.07
    rips
    -0.06
    ustum
    -0.06
    rip
    -0.06
    nah
    -0.06
    eck
    -0.06
    759
    -0.06
    ÄĻk
    -0.06
    uvo
    -0.06
    оÑĢе
    -0.06
    POSITIVE LOGITS
     Tribal
    0.06
    onn
    0.06
    .Utc
    0.06
    ÅŁam
    0.06
    argo
    0.06
    CHA
    0.06
    AXB
    0.06
    arten
    0.06
    xDA
    0.06
    lix
    0.06
    Activations Density 0.002%

    No Known Activations