© 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. 92381
    Prev
    Next
    INDEX
    Explanations

    phrases related to a quest or search for higher understanding or justice

    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
    keit
    -0.09
    asan
    -0.08
    ITY
    -0.08
    ity
    -0.07
    ales
    -0.07
    idence
    -0.07
    quier
    -0.07
    richt
    -0.06
    ugo
    -0.06
    amu
    -0.06
    POSITIVE LOGITS
    IONS
    0.10
    ing
    0.09
    ions
    0.08
    é¡Į
    0.08
    acular
    0.08
    ени
    0.07
    ivals
    0.07
    anova
    0.07
    148
    0.07
    ByExample
    0.07
    Activations Density 0.005%

    No Known Activations