© 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. 118838
    Prev
    Next
    INDEX
    Explanations

    patterns or occurrences of numerical data

    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
    ̣
    -0.07
     же
    -0.07
    ajo
    -0.07
    Ñıж
    -0.06
    ubar
    -0.06
     áº
    -0.06
    izar
    -0.06
    anness
    -0.06
    iel
    -0.06
    áº
    -0.06
    POSITIVE LOGITS
    MarshalAs
    0.06
    #
    0.06
    Insensitive
    0.06
    ouri
    0.06
    -rad
    0.06
    isia
    0.06
    Ïģιά
    0.06
    #ab
    0.06
    /vnd
    0.06
    IVAL
    0.06
    Activations Density 0.002%

    No Known Activations