© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 88700
    Prev
    Next
    INDEX
    Explanations

    structural elements in programming or code

    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
    _allocated
    -0.06
    मत
    -0.06
     commission
    -0.06
    _flutter
    -0.06
    isz
    -0.06
    IFORM
    -0.06
    hrad
    -0.06
    Commission
    -0.06
    	trigger
    -0.06
    [src
    -0.06
    POSITIVE LOGITS
    //{{
    0.07
    erval
    0.07
    laden
    0.06
    .Inject
    0.06
    outh
    0.06
    din
    0.06
     Vin
    0.06
    ارات
    0.06
     CSC
    0.06
    Æ°
    0.06
    Activations Density 0.001%

    No Known Activations