© 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 EvalsExportsinterp-engineNEWAPI 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. 120767
    Prev
    Next
    INDEX
    Explanations

    references to privacy policies and data protection

    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
    adia
    -0.08
    media
    -0.07
    ettel
    -0.07
    mor
    -0.06
    boa
    -0.06
    GroupBox
    -0.06
    mae
    -0.06
     Syndrome
    -0.06
    åĿĽ
    -0.06
     Yönetim
    -0.06
    POSITIVE LOGITS
    ÄĻ
    0.07
    arus
    0.07
    NgModule
    0.06
    yles
    0.06
    ayla
    0.06
    ária
    0.06
    claimer
    0.06
     Returned
    0.06
    _slope
    0.06
     poil
    0.06
    Activations Density 0.002%

    No Known Activations