© 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. 60945
    Prev
    Next
    INDEX
    Explanations

    concepts related to data, systems, and interconnections within various contexts

    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
     Greene
    -0.06
    arith
    -0.06
    uelle
    -0.06
    룬
    -0.06
    uz
    -0.06
    glob
    -0.06
     arrangement
    -0.06
    ffen
    -0.06
    رخ
    -0.06
    pler
    -0.05
    POSITIVE LOGITS
    .Îł
    0.08
    ]={↵
    0.07
    yleft
    0.07
    oplevel
    0.07
    ugins
    0.07
    ç¿Ķ
    0.07
    inalg
    0.07
    ảng
    0.07
    ži
    0.07
    relu
    0.06
    Activations Density 0.068%

    No Known Activations