© 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. 71191
    Prev
    Next
    INDEX
    Explanations

    references to community involvement and interfaith activities

    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
    aret
    -0.07
    stoi
    -0.06
    atre
    -0.06
    atak
    -0.06
    .INSTANCE
    -0.06
     ('
    -0.06
    kker
    -0.06
    UF
    -0.06
    shield
    -0.06
    xies
    -0.06
    POSITIVE LOGITS
    ,www
    0.08
    εÏħ
    0.07
     equipments
    0.07
    -mult
    0.07
    currentColor
    0.06
    аÐ
    0.06
    gend
    0.06
    linkplain
    0.06
    XHR
    0.06
     mainstream
    0.06
    Activations Density 0.001%

    No Known Activations