© 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. 71267
    Prev
    Next
    INDEX
    Explanations

    patterns associated with structured or poetic text elements

    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
    ÑģеÑĢ
    -0.07
    legant
    -0.06
    igte
    -0.06
    nier
    -0.06
    orm
    -0.06
    ghan
    -0.06
    åĺ
    -0.05
    oster
    -0.05
    ORM
    -0.05
    abus
    -0.05
    POSITIVE LOGITS
    ç¹ģ
    0.07
    ungs
    0.07
    appen
    0.07
    znik
    0.06
    thouse
    0.06
    unset
    0.06
    .setResult
    0.06
    linger
    0.06
    vala
    0.06
    (jq
    0.06
    Activations Density 0.002%

    No Known Activations