© 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. 118348
    Prev
    Next
    INDEX
    Explanations

    expressions related to boolean logic and mathematical operations

    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
     zad
    -0.08
    ì²
    -0.07
    ULA
    -0.07
    USAGE
    -0.07
    Thunk
    -0.07
    fastcall
    -0.07
    SCII
    -0.07
    /tcp
    -0.07
    linger
    -0.07
    /target
    -0.07
    POSITIVE LOGITS
     Boolean
    0.08
    _logic
    0.07
     Logic
    0.07
     falsehood
    0.07
    Boolean
    0.07
    Logic
    0.07
     false
    0.06
     logic
    0.06
     Truth
    0.06
     toggle
    0.06
    Activations Density 0.022%

    No Known Activations