© 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. 92926
    Prev
    Next
    INDEX
    Explanations

    expressions and themes related to struggle and the desire for understanding or acceptance

    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
    -0.07
    imli
    -0.07
    lemen
    -0.07
    оÑıн
    -0.07
    hes
    -0.07
    named
    -0.06
    LOY
    -0.06
    NCY
    -0.06
    udget
    -0.06
    abox
    -0.06
    POSITIVE LOGITS
    úsqueda
    0.08
     Král
    0.06
    å¼ĺ
    0.06
    åª
    0.06
    HING
    0.06
    standing
    0.06
     doing
    0.06
    :\/\/
    0.06
    ĵį
    0.06
     discounted
    0.06
    Activations Density 0.075%

    No Known Activations