© 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. 15-LLAMASCOPE-RES-131K
    11. 88665
    Prev
    Next
    INDEX
    Explanations

    details regarding costs and expenses

    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
    eson
    -0.07
    assel
    -0.07
    addListener
    -0.07
    ertino
    -0.07
    è¨Ĥ
    -0.07
    afort
    -0.06
    íģ
    -0.06
    Å¡la
    -0.06
     аналог
    -0.06
    豪
    -0.06
    POSITIVE LOGITS
    loquent
    0.07
     account
    0.06
    jez
    0.06
     annual
    0.06
    Ñľ
    0.06
    rchive
    0.06
     steps
    0.06
     Sadd
    0.06
     option
    0.06
    /tos
    0.06
    Activations Density 0.000%

    No Known Activations