© 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. 116833
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of abundance or magnitude

    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
    /place
    -0.07
    ernen
    -0.07
    screen
    -0.07
    ych
    -0.07
    اÙĨÙĩ
    -0.06
    üçük
    -0.06
    oir
    -0.06
    æ³Ĭ
    -0.06
    sworth
    -0.06
    ses
    -0.06
    POSITIVE LOGITS
    -than
    0.19
     than
    0.16
    _than
    0.14
    than
    0.13
     THAN
    0.12
     Than
    0.11
     вÑģего
    0.10
    Than
    0.10
     niż
    0.10
    idge
    0.10
    Activations Density 0.011%

    No Known Activations