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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 41643
    Prev
    Next
    INDEX
    Explanations

    instances of negation and inability

    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
    hazi
    -0.06
     armor
    -0.06
     change
    -0.06
    avs
    -0.06
    agate
    -0.06
    Fallback
    -0.05
     being
    -0.05
    istine
    -0.05
     Change
    -0.05
    ÙĪرت
    -0.05
    POSITIVE LOGITS
    xis
    0.08
    ukes
    0.08
    opis
    0.07
    aign
    0.07
    AINS
    0.07
    HWND
    0.07
    Ľ°
    0.07
    OUN
    0.07
     tìm
    0.07
    unks
    0.07
    Activations Density 0.012%

    No Known Activations