© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77000
    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
    olin
    -0.08
    thumbnails
    -0.07
     ì§
    -0.07
    üçük
    -0.07
    aver
    -0.07
    _fx
    -0.07
    iná
    -0.07
    缮çļĦ
    -0.07
    анÑĮ
    -0.07
    ÑĪиб
    -0.07
    POSITIVE LOGITS
     share
    0.07
     bundle
    0.06
     Sands
    0.06
     worse
    0.06
     splits
    0.06
    ifié
    0.06
    Switch
    0.06
    两人
    0.05
    èĪĮ
    0.05
    switch
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.