© 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. 118650
    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
    IRE
    -0.06
     worldwide
    -0.06
    580
    -0.06
    Guard
    -0.06
     заÑħ
    -0.06
    eneg
    -0.06
    yh
    -0.06
    CSI
    -0.06
    lobal
    -0.06
     Axios
    -0.06
    POSITIVE LOGITS
    oucher
    0.07
    argas
    0.06
    esz
    0.06
    experiment
    0.06
     McM
    0.06
    empo
    0.06
     æĴ
    0.06
    cene
    0.06
    BaseContext
    0.06
    _dicts
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.