© 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. 125247
    Prev
    Next
    INDEX
    Explanations

    phrases related to expert services and solutions

    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
    wner
    -0.06
     isNaN
    -0.06
    TEMPL
    -0.06
     lah
    -0.06
    .lab
    -0.06
     Sanayi
    -0.06
     пÑĢеÑģ
    -0.06
     hoá
    -0.06
    rase
    -0.06
    issement
    -0.06
    POSITIVE LOGITS
    ereco
    0.07
    ï¸ı
    0.07
    oret
    0.07
    thers
    0.06
    aro
    0.06
    pel
    0.06
    orem
    0.06
    895
    0.06
     mech
    0.06
    tes
    0.06
    Activations Density 0.030%

    No Known Activations