© 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. 72464
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, particularly spouses and partners

    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
    acters
    -0.07
    illa
    -0.07
    uler
    -0.07
    лÑİ
    -0.07
    anged
    -0.06
    ứng
    -0.06
    WithEmail
    -0.06
    áÄį
    -0.06
    opes
    -0.06
    beits
    -0.06
    POSITIVE LOGITS
     who
    0.07
     æľ¨
    0.06
     whom
    0.06
    obb
    0.06
    zig
    0.06
    ãĥªãĤ¹
    0.06
     sokak
    0.06
    Uvs
    0.06
    uele
    0.06
    620
    0.06
    Activations Density 0.007%

    No Known Activations