© 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. 106269
    Prev
    Next
    INDEX
    Explanations

    key terms related to data storage and management

    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
     Eins
    -0.08
    ToPoint
    -0.07
    ÑĢаÑħов
    -0.07
    leitung
    -0.07
     Nah
    -0.07
    anye
    -0.07
    еви
    -0.06
     trh
    -0.06
    .tim
    -0.06
    ourcing
    -0.06
    POSITIVE LOGITS
    à¹Ħว
    0.10
     permanently
    0.08
    adera
    0.07
     somewhere
    0.07
    Permanent
    0.07
    ODO
    0.07
     Storage
    0.06
     permanent
    0.06
     Ñģебе
    0.06
     storage
    0.06
    Activations Density 0.050%

    No Known Activations