© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74513
    Prev
    Next
    INDEX
    Explanations

    critical perspectives on arguments and claims, particularly regarding evidence and personal belief systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    thouse
    -0.07
    emachine
    -0.07
    Ń
    -0.07
    erdale
    -0.06
    ahun
    -0.06
    indow
    -0.06
    инов
    -0.06
    ej
    -0.06
     Lov
    -0.06
     UIScreen
    -0.06
    POSITIVE LOGITS
    Cargo
    0.07
    âĢIJ
    0.06
    Liter
    0.06
     Liter
    0.06
    ObjectName
    0.06
    iche
    0.06
    EventType
    0.06
    fec
    0.06
    OTTOM
    0.06
    uely
    0.06
    Activations Density 0.016%

    No Known Activations