© 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. 5455
    Prev
    Next
    INDEX
    Explanations

    terms related to roles, responsibilities, and societal structures

    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
    itere
    -0.07
    tingham
    -0.07
    plat
    -0.06
    okane
    -0.06
     Bottom
    -0.06
    landing
    -0.06
    aupt
    -0.06
    éĶĭ
    -0.06
     serge
    -0.06
     Roose
    -0.06
    POSITIVE LOGITS
    ebra
    0.07
    /std
    0.06
    óng
    0.06
    imu
    0.06
    upos
    0.06
    awi
    0.06
     Uk
    0.06
    ffd
    0.06
    ç«
    0.06
    eros
    0.06
    Activations Density 0.001%

    No Known Activations