© 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. 118325
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ActionTypes
    -0.06
    803
    -0.06
     whilst
    -0.06
    ment
    -0.06
    _ENSURE
    -0.06
     Rever
    -0.06
    491
    -0.06
    loyd
    -0.06
    éŁ
    -0.06
    ÅĤug
    -0.05
    POSITIVE LOGITS
     jadx
    0.08
    /*č↵
    0.08
     èĻ
    0.08
    .EventQueue
    0.07
    ADX
    0.07
    á»ĥn
    0.07
    itus
    0.06
     Gov
    0.06
    ulfilled
    0.06
    icensed
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.