© 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 EvalsExportsinterp-engineNEWAPI 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. 39480
    Prev
    Next
    INDEX
    Explanations

    information related to schedules and availability for lessons or services

    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
    azar
    -0.07
    baugh
    -0.06
    585
    -0.06
    ourke
    -0.06
    ledge
    -0.06
    atura
    -0.06
    ptic
    -0.06
     Soph
    -0.06
    олж
    -0.06
    328
    -0.06
    POSITIVE LOGITS
    arges
    0.06
     facility
    0.06
    chaft
    0.06
    naÄį
    0.06
     Facilities
    0.06
    تس
    0.06
    igr
    0.06
     Facility
    0.06
    Rent
    0.06
    Hora
    0.06
    Activations Density 0.001%

    No Known Activations