© 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. 15-LLAMASCOPE-RES-131K
    11. 62303
    Prev
    Next
    INDEX
    Explanations

    specific address formats including street and building information

    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
    ctor
    -0.07
    ilig
    -0.07
    kate
    -0.07
    ptic
    -0.06
    uche
    -0.06
    ichi
    -0.06
    igel
    -0.06
    iger
    -0.06
    anga
    -0.06
    moth
    -0.06
    POSITIVE LOGITS
    ideon
    0.07
    efault
    0.06
     coll
    0.06
    á»Ļt
    0.06
    _misc
    0.06
    antor
    0.06
    emap
    0.06
    лоÑĢ
    0.06
    ¢
    0.06
    innacle
    0.06
    Activations Density 0.005%

    No Known Activations