© 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. 3176
    Prev
    Next
    INDEX
    Explanations

    terms related to survival and emergency preparedness

    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
    edly
    -0.08
    gow
    -0.08
    alat
    -0.07
    eka
    -0.07
    uras
    -0.07
    mia
    -0.07
    /software
    -0.07
    atura
    -0.07
    retch
    -0.06
    etur
    -0.06
    POSITIVE LOGITS
    ship
    0.09
    ivors
    0.09
     instinct
    0.08
    /ext
    0.07
    ably
    0.07
    ists
    0.07
     instincts
    0.07
    arez
    0.07
    ist
    0.07
    istik
    0.06
    Activations Density 0.010%

    No Known Activations