© 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. 15-LLAMASCOPE-RES-131K
    11. 27420
    Prev
    Next
    INDEX
    Explanations

    references to UNESCO World Heritage Sites

    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
    aternity
    -0.06
    tracker
    -0.06
    caster
    -0.06
    á»ĩnh
    -0.06
    steen
    -0.06
     Mug
    -0.05
    etat
    -0.05
    anded
    -0.05
    abyrinth
    -0.05
    coop
    -0.05
    POSITIVE LOGITS
    hlen
    0.08
    unsch
    0.08
    CATEGORY
    0.07
     reb
    0.07
    uÄį
    0.06
     Sac
    0.06
    ignon
    0.06
     joint
    0.06
    zÄĻ
    0.06
    ülen
    0.06
    Activations Density 0.003%

    No Known Activations