© 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. 57418
    Prev
    Next
    INDEX
    Explanations

    formatting or structural elements in code comments

    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
    opoulos
    -0.08
    aný
    -0.07
    herits
    -0.07
    ecz
    -0.07
     ÏĢÏīÏĤ
    -0.07
     eskort
    -0.07
    jang
    -0.07
     Interracial
    -0.07
    WithOptions
    -0.06
    InThe
    -0.06
    POSITIVE LOGITS
     off
    0.06
    ce
    0.06
    azo
    0.06
    ile
    0.06
    otto
    0.06
    CLUDING
    0.05
     ug
    0.05
    feeding
    0.05
    apan
    0.05
     ç»
    0.05
    Activations Density 0.016%

    No Known Activations