© 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. 56200
    Prev
    Next
    INDEX
    Explanations

    features related to class and access control 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
    OA
    -0.07
    aksi
    -0.07
     CircularProgress
    -0.06
     beden
    -0.06
     sophistic
    -0.06
    aho
    -0.06
    $MESS
    -0.06
    apis
    -0.06
    apiro
    -0.06
    oe
    -0.06
    POSITIVE LOGITS
    ovna
    0.07
    ror
    0.06
     nackte
    0.06
     subrange
    0.06
    Clipboard
    0.06
    erable
    0.06
    ëį°
    0.06
    buie
    0.06
    usra
    0.06
    MethodImpl
    0.06
    Activations Density 0.001%

    No Known Activations