© 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. 9-LLAMASCOPE-RES-131K
    11. 94467
    Prev
    Next
    INDEX
    Explanations

    roles related to dance and music, particularly focusing on positions and titles within orchestras and dance companies

    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
    اض
    -0.08
    utow
    -0.07
    #echo
    -0.07
    oken
    -0.07
    errmsg
    -0.07
    aset
    -0.07
    ToLocal
    -0.07
     derec
    -0.07
    LIKELY
    -0.07
    ataka
    -0.07
    POSITIVE LOGITS
    Y
    0.06
    I
    0.06
    viron
    0.06
     Wik
    0.05
     Fol
    0.05
    ur
    0.05
     colleg
    0.05
    PI
    0.05
     Weber
    0.05
    urer
    0.05
    Activations Density 0.006%

    No Known Activations