© 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. 128260
    Prev
    Next
    INDEX
    Explanations

    references to collaborative international partnerships or organizations

    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
    ichern
    -0.07
    azio
    -0.06
    abant
    -0.06
    upply
    -0.06
    axter
    -0.06
    /classes
    -0.06
    ông
    -0.06
    ellular
    -0.06
    otine
    -0.06
     Diy
    -0.06
    POSITIVE LOGITS
     science
    0.07
     обÑģ
    0.07
    aug
    0.06
     desi
    0.06
    VL
    0.06
    TEL
    0.06
    çŀ
    0.06
    riba
    0.06
     downtime
    0.06
     instrument
    0.06
    Activations Density 0.014%

    No Known Activations