© 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 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. 15-LLAMASCOPE-RES-131K
    11. 88370
    Prev
    Next
    INDEX
    Explanations

    terms related to invasion and intrusion

    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
    ondo
    -0.08
     avent
    -0.08
    ç±
    -0.08
    afia
    -0.07
    elsen
    -0.07
    ouro
    -0.07
    ково
    -0.07
    ÐķС
    -0.07
    ØŃÙĬ
    -0.07
     Affero
    -0.07
    POSITIVE LOGITS
     into
    0.10
     Into
    0.08
     INTO
    0.07
     invasion
    0.07
    Into
    0.07
     intrusion
    0.07
     double
    0.06
    into
    0.06
    reach
    0.06
    ãģĤãĤĬãģĮãģ¨ãģĨ
    0.06
    Activations Density 0.060%

    No Known Activations