© 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. 62744
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal or account information

    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
    iaux
    -0.08
    icerca
    -0.08
    ÑĦеÑĢ
    -0.08
    ÙĪÙĨا
    -0.07
    asca
    -0.07
    ovel
    -0.07
    ROTO
    -0.07
     kalp
    -0.07
    ReturnType
    -0.07
    oly
    -0.07
    POSITIVE LOGITS
     including
    0.08
     necessary
    0.07
    including
    0.07
     such
    0.07
     Including
    0.07
     crown
    0.06
     INCLUDING
    0.06
    åĮħæĭ¬
    0.06
    agar
    0.06
     required
    0.06
    Activations Density 0.014%

    No Known Activations