© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 641
    Prev
    Next
    INDEX
    Explanations

    terms related to danger and risk

    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
    /basic
    -0.07
    ObjectContext
    -0.06
    uplic
    -0.06
     backgroundImage
    -0.06
    aret
    -0.06
    sek
    -0.06
    aits
    -0.06
    .preference
    -0.06
    ammer
    -0.06
    emble
    -0.06
    POSITIVE LOGITS
     danger
    0.12
     dangers
    0.10
     tendency
    0.10
     tendencies
    0.10
     Danger
    0.10
     traps
    0.10
     trap
    0.10
    eware
    0.09
     temptation
    0.09
    danger
    0.07
    Activations Density 0.151%

    No Known Activations