© 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. 30483
    Prev
    Next
    INDEX
    Explanations

    references to classic or timeless items, particularly in the context of cars and films

    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
    ìĦľ
    -0.07
    isan
    -0.07
     latest
    -0.07
    jar
    -0.06
    to
    -0.06
    Ø
    -0.06
    ãģįãģŁ
    -0.06
    thing
    -0.06
     Colomb
    -0.06
    ÑģÑĤÑĢо
    -0.06
    POSITIVE LOGITS
    /original
    0.11
    âĢĮترÛĮÙĨ
    0.08
    /current
    0.08
     ترÛĮÙĨ
    0.08
    /mod
    0.08
    NECT
    0.08
    /class
    0.07
    rd
    0.07
    opoulos
    0.07
    ardy
    0.07
    Activations Density 0.012%

    No Known Activations