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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3803
    Prev
    Next
    INDEX
    Explanations

    elements related to cybersecurity and online account security measures

    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
    arching
    -0.06
    缴
    -0.06
    ABEL
    -0.06
     actionTypes
    -0.06
    tran
    -0.06
    quat
    -0.06
     Qui
    -0.06
     Pic
    -0.06
    hea
    -0.06
    eson
    -0.06
    POSITIVE LOGITS
    adla
    0.07
    éį
    0.07
     requirement
    0.06
     Require
    0.06
    security
    0.06
    _require
    0.06
     Required
    0.06
     security
    0.06
     forgotten
    0.06
    _required
    0.06
    Activations Density 0.004%

    No Known Activations