© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77944
    Prev
    Next
    INDEX
    Explanations

    commands related to object allocation and initialization 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
    vel
    -0.06
    489
    -0.06
    awan
    -0.06
    reh
    -0.06
    086
    -0.06
     ust
    -0.06
     meteor
    -0.06
     Borg
    -0.06
    762
    -0.06
     Weather
    -0.06
    POSITIVE LOGITS
    èĬ³
    0.07
     Redirect
    0.07
     initWith
    0.07
    Forgery
    0.07
    .getInstance
    0.07
    isted
    0.07
    .allocate
    0.07
    .useState
    0.07
    ownik
    0.07
    avern
    0.07
    Activations Density 0.004%

    No Known Activations