© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129931
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements or data

    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
    ptal
    -0.07
    OAD
    -0.07
    infos
    -0.06
    bud
    -0.06
    кÑĢа
    -0.06
    Ñīей
    -0.06
    еÑĨ
    -0.06
    oa
    -0.06
    udeau
    -0.06
    λον
    -0.06
    POSITIVE LOGITS
     interchange
    0.07
     Albert
    0.06
    Albert
    0.06
    uti
    0.06
    580
    0.06
     Rican
    0.06
     Fletcher
    0.06
    ModelProperty
    0.06
    tlement
    0.06
     Jacqu
    0.06
    Activations Density 0.003%

    No Known Activations