© 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. 9-LLAMASCOPE-RES-131K
    11. 95063
    Prev
    Next
    INDEX
    Explanations

    references to statistical data and reports

    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
    esi
    -0.07
    ering
    -0.07
     Pend
    -0.07
    idth
    -0.07
    aded
    -0.06
    ana
    -0.06
    owitz
    -0.06
    atha
    -0.06
    alias
    -0.06
     essay
    -0.06
    POSITIVE LOGITS
    eum
    0.07
    ekler
    0.07
    etty
    0.07
    rema
    0.07
    AUSE
    0.06
     اÛĮÙĨÚ©Ùĩ
    0.06
    éĥİ
    0.06
    .Bounds
    0.06
    maz
    0.06
    uales
    0.06
    Activations Density 0.025%

    No Known Activations