© 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. 70842
    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
     Rig
    -0.07
    ette
    -0.06
     POLITICO
    -0.06
     virtually
    -0.06
     atleast
    -0.06
     Merk
    -0.06
     Pepper
    -0.05
    akis
    -0.05
     stmt
    -0.05
     trú
    -0.05
    POSITIVE LOGITS
     Maj
    0.08
    izoph
    0.08
    quate
    0.07
    \brief
    0.07
    rottle
    0.07
    conds
    0.07
    agma
    0.07
    branch
    0.06
    ÄĻp
    0.06
    ÙĬØ´
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.