© 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. 87090
    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
    oten
    -0.07
    akis
    -0.06
    ewan
    -0.06
    ovah
    -0.06
     assoc
    -0.06
    IED
    -0.06
    mitt
    -0.06
    ansa
    -0.06
    zar
    -0.06
    quests
    -0.06
    POSITIVE LOGITS
    XHR
    0.06
    elda
    0.06
     Martial
    0.06
     Bilim
    0.06
     Dien
    0.06
    ัà¸ģà¸Ķ
    0.06
    rve
    0.06
    /vnd
    0.06
    æĮĻ
    0.06
    mazon
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.