© 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 EvalsExportsinterp-engineNEWAPI 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. 121163
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to user actions and interactions in programming contexts

    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
    lux
    -0.08
    erti
    -0.07
    prav
    -0.07
    uti
    -0.07
     Placement
    -0.07
    odÃŃ
    -0.06
    论åĿĽ
    -0.06
    ounder
    -0.06
    bat
    -0.06
    ounds
    -0.06
    POSITIVE LOGITS
    @email
    0.07
     want
    0.07
    anni
    0.06
     created
    0.06
    ignon
    0.06
     used
    0.06
     call
    0.06
    heritance
    0.06
    Backdrop
    0.06
    RIA
    0.05
    Activations Density 0.014%

    No Known Activations