© 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. 58510
    Prev
    Next
    INDEX
    Explanations

    references to spending time with family and others

    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
    chn
    -0.08
    ̣
    -0.08
    缤
    -0.07
    ocos
    -0.07
    ÌĨ
    -0.07
    isz
    -0.07
    ogui
    -0.07
    gent
    -0.07
    reopen
    -0.07
    dn
    -0.07
    POSITIVE LOGITS
     family
    0.08
    leton
    0.08
    ABCDEFGHIJKLMNOP
    0.07
     friends
    0.07
    ought
    0.06
     fam
    0.06
    Margins
    0.06
     nhau
    0.06
    /pay
    0.06
    edral
    0.06
    Activations Density 0.011%

    No Known Activations