© 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. 105256
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantity or frequency

    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
    stoup
    -0.07
     âĨĶ
    -0.07
    znam
    -0.07
     ÐijоÑĢ
    -0.07
    ãĤ©
    -0.06
    ovky
    -0.06
     kür
    -0.06
    вай
    -0.06
     Quiet
    -0.06
    erties
    -0.06
    POSITIVE LOGITS
     two
    0.07
    fold
    0.06
    одав
    0.06
    quals
    0.06
    éal
    0.06
    ountains
    0.06
    kan
    0.06
    ulling
    0.06
    icone
    0.06
    Helpers
    0.05
    Activations Density 0.011%

    No Known Activations