© 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. 83477
    Prev
    Next
    INDEX
    Explanations

    references to popular media titles, particularly in relation to movies and TV shows

    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
    åĻ¨
    -0.07
    оÑĤÑĮ
    -0.07
    ifice
    -0.06
    новид
    -0.06
    urope
    -0.06
    اÙĨÙĩ
    -0.06
    imonial
    -0.06
    eshire
    -0.06
    ìĹŃìĭľ
    -0.06
    (DBG
    -0.06
    POSITIVE LOGITS
    mania
    0.07
    olik
    0.07
     MetroFramework
    0.06
     же
    0.06
    declspec
    0.06
    .nlm
    0.06
    affles
    0.06
    ego
    0.06
    vangst
    0.06
    .Formatting
    0.06
    Activations Density 0.078%

    No Known Activations