© 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. 40061
    Prev
    Next
    INDEX
    Explanations

    references to data structures and entities in code

    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
    anda
    -0.07
    igne
    -0.07
    -layout
    -0.07
    izational
    -0.07
     Composition
    -0.07
    stre
    -0.06
    ables
    -0.06
    sdale
    -0.06
    873
    -0.06
    ingham
    -0.06
    POSITIVE LOGITS
    arith
    0.07
    STYPE
    0.06
    egt
    0.06
    LLL
    0.06
    лл
    0.06
    лий
    0.06
    0.06
    æŁ´
    0.06
     Morris
    0.06
    ÑĢÑĥÑĩ
    0.06
    Activations Density 0.001%

    No Known Activations