© 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. 22-LLAMASCOPE-RES-131K
    11. 3655
    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
    oya
    -0.07
    atch
    -0.07
    /misc
    -0.06
    asu
    -0.06
    ä¸ĺ
    -0.06
    ĽĦ
    -0.06
     redd
    -0.06
     people
    -0.06
     Dam
    -0.06
    ÑĢÑĥÑģ
    -0.06
    POSITIVE LOGITS
    appropri
    0.07
    -learning
    0.07
    AILS
    0.07
    æİĪ
    0.06
     skills
    0.06
    íĹĪ
    0.06
    ponge
    0.06
     learners
    0.06
    eor
    0.06
    quina
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.