© 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. 58215
    Prev
    Next
    INDEX
    Explanations

    expressions of existential concern and the dynamics of faith and spirituality

    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
    atsu
    -0.07
    blr
    -0.07
    UNS
    -0.07
    OLLOW
    -0.07
    ania
    -0.07
    uben
    -0.07
    SCORE
    -0.07
    ube
    -0.07
    ç²
    -0.06
    ona
    -0.06
    POSITIVE LOGITS
     otherwise
    0.07
     so
    0.07
    $MESS
    0.07
     tolik
    0.06
     Latter
    0.06
     hed
    0.06
     promise
    0.06
     abandon
    0.06
     elsewhere
    0.06
    pent
    0.06
    Activations Density 0.026%

    No Known Activations