© 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. 128906
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal growth and knowledge acquisition over time

    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
    ClientId
    -0.07
    agers
    -0.07
     biz
    -0.06
    ÏĥÏĦÏĮ
    -0.06
    era
    -0.06
     antidepress
    -0.06
    ç«ĭ
    -0.06
    []{↵
    -0.06
    овеÑĢ
    -0.06
     arm
    -0.06
    POSITIVE LOGITS
    chter
    0.07
    loor
    0.06
    aub
    0.06
    omba
    0.06
    lassian
    0.06
    forcement
    0.06
    ammer
    0.06
    iability
    0.06
    clare
    0.06
    ÑĨÑĮ
    0.06
    Activations Density 0.000%

    No Known Activations