© 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. 62044
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "invasion" and its variations

    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
    atura
    -0.08
    idor
    -0.07
    DNA
    -0.07
    ality
    -0.07
    iams
    -0.07
    aturas
    -0.07
    eron
    -0.07
    862
    -0.07
     sond
    -0.07
    xit
    -0.07
    POSITIVE LOGITS
    -style
    0.07
    TargetException
    0.06
    RIPT
    0.06
    OrUpdate
    0.06
    ãģŁãģı
    0.06
     invasion
    0.06
    ess
    0.06
     priv
    0.06
     Dahl
    0.06
    arel
    0.06
    Activations Density 0.009%

    No Known Activations