© 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. 54971
    Prev
    Next
    INDEX
    Explanations

    references to digital object identifiers (DOIs)

    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
    imming
    -0.07
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.07
    TokenType
    -0.07
    tings
    -0.07
    æī±
    -0.07
    ernote
    -0.07
    OfYear
    -0.07
    ยà¸Ļà¸ķ
    -0.07
    ãģĨãģ¡
    -0.07
    ALSE
    -0.07
    POSITIVE LOGITS
    yen
    0.07
    arty
    0.06
    yas
    0.06
     unfavor
    0.06
    idine
    0.06
    BASE
    0.06
    y
    0.05
    tor
    0.05
    _featured
    0.05
    erved
    0.05
    Activations Density 0.003%

    No Known Activations