© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 74283
    Prev
    Next
    INDEX
    Explanations

    references to experiences or feelings of personal significance

    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
     &
    -0.06
    ă
    -0.06
     televised
    -0.06
     Vác
    -0.06
     Emin
    -0.06
     /*
    -0.06
    °
    -0.06
     wikipedia
    -0.06
     surely
    -0.06
    POSITIVE LOGITS
    ((((
    0.08
     ê²Į
    0.07
    alem
    0.07
    FFFFFFFF
    0.07
    aleb
    0.07
    _bt
    0.07
    bis
    0.07
    ÑģÑĮого
    0.07
    μη
    0.07
    MUX
    0.07
    Activations Density 0.000%

    No Known Activations