© 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. 9-LLAMASCOPE-RES-131K
    11. 96601
    Prev
    Next
    INDEX
    Explanations

    numerical values and specifications related to technical or scientific content

    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
     rel
    -0.06
    OTO
    -0.06
    chrift
    -0.06
    aleza
    -0.06
    ernel
    -0.06
    (object
    -0.06
    ذا
    -0.06
    ç§Ģ
    -0.06
    ried
    -0.06
    Transmission
    -0.05
    POSITIVE LOGITS
    олÑİ
    0.07
    UTERS
    0.07
    аÑĢÑı
    0.07
    nonnull
    0.06
    PyObject
    0.06
    ropic
    0.06
    .started
    0.06
    ÙĴد
    0.06
    imus
    0.06
    idf
    0.06
    Activations Density 0.008%

    No Known Activations