© 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. 84082
    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
    :CGRect
    -0.07
    acht
    -0.06
     wann
    -0.06
    ÅĻet
    -0.06
    ilian
    -0.06
    ová
    -0.06
    .GetResponse
    -0.06
    ibo
    -0.06
    ronics
    -0.06
    lü
    -0.06
    POSITIVE LOGITS
     Experiment
    0.07
    XD
    0.07
     pilots
    0.07
    piler
    0.06
     Camden
    0.06
     Nug
    0.06
    guard
    0.06
    æ··åIJĪ
    0.06
    \grid
    0.06
     Ott
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.