© 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 EvalsExportsinterp-engineNEWAPI 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. 27419
    Prev
    Next
    INDEX
    Explanations

    key details related to film statistics and performance

    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
    ém
    -0.06
     serm
    -0.06
     Agent
    -0.06
    assis
    -0.06
    izio
    -0.06
    ALCHEMY
    -0.06
    .dw
    -0.06
    &m
    -0.06
    磨
    -0.06
    roi
    -0.05
    POSITIVE LOGITS
    inz
    0.07
     Wallace
    0.06
    Å¡t
    0.06
     VÅ¡ech
    0.06
    ioni
    0.06
    μαÏĦο
    0.06
     Sợ
    0.06
    luv
    0.06
    aby
    0.06
    ÏĢοÏĦε
    0.06
    Activations Density 0.000%

    No Known Activations