© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 74428
    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
    erne
    -0.06
    loe
    -0.06
    engkap
    -0.06
    uden
    -0.06
    .aspx
    -0.06
    MSN
    -0.06
    ACES
    -0.06
    ért
    -0.06
     Factor
    -0.06
    ÙĪاÙĨ
    -0.06
    POSITIVE LOGITS
    turnstile
    0.07
    sez
    0.07
     Dent
    0.06
     pornstar
    0.06
     Nass
    0.06
    ÙĬاÙĨ
    0.06
    UAGE
    0.06
     pretext
    0.06
    _UNLOCK
    0.06
    pillar
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.