© 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. 72165
    Prev
    Next
    INDEX
    Explanations

    references to security and surveillance

    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
     Rosenstein
    -0.08
    enga
    -0.08
    AZY
    -0.07
    krv
    -0.07
    ÅĤad
    -0.07
    rana
    -0.07
    è£ľ
    -0.07
    åĿ¦
    -0.07
    ifes
    -0.06
     Pale
    -0.06
    POSITIVE LOGITS
     watch
    0.14
     monitoring
    0.12
     watches
    0.12
     Watch
    0.11
     monitor
    0.11
    Watch
    0.10
     vigil
    0.10
    watch
    0.10
    çĽij
    0.10
     surveillance
    0.10
    Activations Density 0.081%

    No Known Activations