© 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. 17-LLAMASCOPE-RES-131K
    11. 57327
    Prev
    Next
    INDEX
    Explanations

    terms related to constructors and object creation in programming

    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
    683
    -0.07
    ÑĢÑĥÑĤ
    -0.07
    illes
    -0.07
    abee
    -0.06
     subclass
    -0.06
    leet
    -0.06
    yte
    -0.06
    yster
    -0.06
    amer
    -0.06
    hec
    -0.06
    POSITIVE LOGITS
    aln
    0.07
    zenie
    0.07
    ziej
    0.07
    åĩºçīĪ社
    0.06
     doPost
    0.06
    çĽijåIJ¬é¡µéĿ¢
    0.06
    anges
    0.06
    .Aggressive
    0.06
    éĸ¢
    0.06
    ÙĪدÛĮ
    0.06
    Activations Density 0.004%

    No Known Activations