© 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. 90577
    Prev
    Next
    INDEX
    Explanations

    mathematical references and calculations related to formulas and conditions

    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
    thur
    -0.07
    iyon
    -0.07
    bill
    -0.06
    gid
    -0.06
    plex
    -0.06
     Lease
    -0.06
     crushing
    -0.06
    ania
    -0.06
    rient
    -0.06
    isko
    -0.06
    POSITIVE LOGITS
    ovah
    0.08
    .dataTables
    0.06
    undy
    0.06
     dealt
    0.06
    á»ĵn
    0.06
    á»ĵ
    0.05
    calculator
    0.05
     Late
    0.05
    uel
    0.05
    uly
    0.05
    Activations Density 0.008%

    No Known Activations