© 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 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. 58770
    Prev
    Next
    INDEX
    Explanations

    tags within HTML documents

    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
    863
    -0.06
    uely
    -0.06
    zzo
    -0.06
    insky
    -0.06
    ocal
    -0.06
    stoup
    -0.06
    isle
    -0.06
    KF
    -0.06
    prene
    -0.06
    576
    -0.06
    POSITIVE LOGITS
    esel
    0.07
    inded
    0.06
    .getColumnIndex
    0.06
    ØŃاد
    0.06
    itele
    0.06
    ANI
    0.06
    ิà¸ļ
    0.06
    ut
    0.06
     Fram
    0.05
    gd
    0.05
    Activations Density 0.001%

    No Known Activations