© 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. 29682
    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
    _Tis
    -0.07
    Äįit
    -0.07
    odore
    -0.07
    urdy
    -0.06
    Brief
    -0.06
    agoon
    -0.06
    EEK
    -0.06
     Gros
    -0.06
    óm
    -0.06
    .lambda
    -0.06
    POSITIVE LOGITS
     ministry
    0.07
     convict
    0.07
    afc
    0.06
     ÐĿаз
    0.06
     Romans
    0.06
    riott
    0.06
    dds
    0.06
    kar
    0.06
     col
    0.06
     relational
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.