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

    Neuronpedia

    Jacobian LensNEW
    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. 9-LLAMASCOPE-RES-131K
    11. 96972
    Prev
    Next
    INDEX
    Explanations

    class and constructor definitions in code

    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
    antry
    -0.07
    lei
    -0.07
    sons
    -0.07
    olit
    -0.07
     Erotische
    -0.07
    ÃŃs
    -0.06
    -fontawesome
    -0.06
    clair
    -0.06
     åī
    -0.06
    tember
    -0.06
    POSITIVE LOGITS
    oria
    0.07
    oric
    0.06
    elah
    0.06
     ÙĢ
    0.06
    _RAD
    0.06
    orie
    0.06
    ìĶ
    0.06
     NavParams
    0.05
    inel
    0.05
    éĻµ
    0.05
    Activations Density 0.007%

    No Known Activations