© 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. 15597
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time or frequency, particularly emphasizing the concepts of "ever" and "never."

    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
    Ïĥμο
    -0.07
    cÃŃ
    -0.07
     å¯
    -0.07
    udit
    -0.07
    elop
    -0.07
    γκ
    -0.07
    amoto
    -0.07
    еÑģа
    -0.07
    ãĥ¼ãĥ«ãĥī
    -0.07
    ué
    -0.07
    POSITIVE LOGITS
     previously
    0.07
     elsewhere
    0.07
    yet
    0.06
     previous
    0.06
    رÙĪع
    0.06
    endl
    0.06
     amount
    0.06
    оÑĤи
    0.06
    before
    0.06
    .gca
    0.06
    Activations Density 0.003%

    No Known Activations