© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125304
    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
     inval
    -0.07
    agar
    -0.06
    uthor
    -0.06
     Bucket
    -0.06
    ìłĢ
    -0.06
     nab
    -0.06
    berg
    -0.06
     :-
    -0.06
    andal
    -0.05
    anye
    -0.05
    POSITIVE LOGITS
    ESSAGES
    0.07
    ìĿ´ì§Ģ
    0.07
    ãĥ¼ãĥ«ãĥī
    0.07
    对æĸ¹
    0.06
    otas
    0.06
    оз
    0.06
    .LookAndFeel
    0.06
     upbeat
    0.06
    .weixin
    0.06
    oji
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.