© 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 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. 71264
    Prev
    Next
    INDEX
    Explanations

    HTML structure and elements

    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
    cene
    -0.07
     }}/
    -0.06
    æ¶
    -0.06
    ungle
    -0.06
    оÑģÑĤав
    -0.06
    shal
    -0.06
    ania
    -0.06
    antro
    -0.06
    udem
    -0.06
    anya
    -0.06
    POSITIVE LOGITS
    erin
    0.07
    ÑĭÑĪ
    0.07
    alian
    0.06
    ines
    0.06
     kra
    0.06
    ãģ¿ãģŁãģĦ
    0.06
    .datasource
    0.06
    ake
    0.05
    qp
    0.05
    afs
    0.05
    Activations Density 0.008%

    No Known Activations