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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127896
    Prev
    Next
    INDEX
    Explanations

    descriptions of living conditions and basic necessities

    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
    arendra
    -0.08
    essel
    -0.07
    #
    -0.07
    clare
    -0.07
    aceous
    -0.06
    åĿĬ
    -0.06
    uzzle
    -0.06
    /fw
    -0.06
    escort
    -0.06
    neh
    -0.06
    POSITIVE LOGITS
    ooks
    0.07
     electricity
    0.07
     cooking
    0.07
     Electricity
    0.07
    -earth
    0.07
     SHARES
    0.07
     rud
    0.07
     improvised
    0.06
    agua
    0.06
    鼨
    0.06
    Activations Density 0.015%

    No Known Activations