© 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. 2098
    Prev
    Next
    INDEX
    Explanations

    actions related to intrusion and access breaches

    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
    ÐķС
    -0.08
    :;↵
    -0.07
    .Dto
    -0.07
    çIJ
    -0.07
    iless
    -0.07
    xies
    -0.07
    .Dot
    -0.07
     pione
    -0.07
    ãģ«ãģ¤
    -0.07
    utow
    -0.07
    POSITIVE LOGITS
     into
    0.08
     closed
    0.08
    closed
    0.06
     via
    0.06
    _closed
    0.06
     compound
    0.06
     and
    0.06
    via
    0.06
     Into
    0.06
    losed
    0.06
    Activations Density 0.024%

    No Known Activations