© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127634
    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
    áp
    -0.07
    hazi
    -0.06
     multis
    -0.06
     vs
    -0.06
     Doctrine
    -0.06
    etur
    -0.06
    KeyEvent
    -0.05
     might
    -0.05
     ![
    -0.05
    agua
    -0.05
    POSITIVE LOGITS
    ÅĻet
    0.07
    飯
    0.06
    dek
    0.06
     tavs
    0.06
    Normals
    0.06
    æ¦ľ
    0.06
     Belly
    0.06
     billeder
    0.06
    ades
    0.06
     Mime
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.