© 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. 60071
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with guardianship abuse and legal issues related to it

    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
    iris
    -0.07
     prosecuting
    -0.07
     pard
    -0.06
    unal
    -0.06
    TRACE
    -0.06
    /WebAPI
    -0.06
    à¸Ĺาà¸ĩà¸ģาร
    -0.06
     Vys
    -0.06
     Thursday
    -0.06
    Ìī
    -0.06
    POSITIVE LOGITS
    ngen
    0.07
    alet
    0.07
    -addon
    0.07
    Mathf
    0.06
    ãĤ¤ãĥ³ãĥĪ
    0.06
    æĮ¯ãĤĬ
    0.06
    onaut
    0.06
    ĵåIJį
    0.06
    à¥Įन
    0.06
    auté
    0.06
    Activations Density 0.005%

    No Known Activations