© 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 EvalsExportsAPI 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. 57395
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly those associated with various achievements or roles

    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
    ington
    -0.07
    orro
    -0.07
    dera
    -0.07
    ÎŃν
    -0.07
    AdminController
    -0.07
    ноÑģÑı
    -0.07
     DISPATCH
    -0.07
    _dispatch
    -0.07
    attr
    -0.06
     dispatch
    -0.06
    POSITIVE LOGITS
     Jr
    0.10
     III
    0.09
     II
    0.07
    III
    0.07
    opup
    0.06
    verts
    0.06
     IV
    0.06
    elop
    0.06
    II
    0.06
    ogene
    0.06
    Activations Density 0.061%

    No Known Activations