© 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. 59198
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers regarding liability and responsibility

    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
    atat
    -0.07
    atemala
    -0.07
    zsche
    -0.07
    elin
    -0.07
     ordin
    -0.06
    ovie
    -0.06
    ata
    -0.06
    ÑĢеÑģÑĤ
    -0.06
    ¼
    -0.06
    abajo
    -0.06
    POSITIVE LOGITS
    .generated
    0.08
    CLUD
    0.07
    macros
    0.06
    _Helper
    0.06
    ÙĪبÛĮ
    0.06
    Endian
    0.06
    ipline
    0.06
    óz
    0.06
    ÑĨÑĸйнÑĸ
    0.06
     Unsupported
    0.06
    Activations Density 0.001%

    No Known Activations