© 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. 92893
    Prev
    Next
    INDEX
    Explanations

    references to metrics and measurements related to performance and efficiency in 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
     bout
    -0.07
    gesch
    -0.07
    ((__
    -0.06
    ÑģÑĤе
    -0.06
    255
    -0.06
    rias
    -0.06
    .Condition
    -0.06
    rik
    -0.06
    .nano
    -0.06
    iesz
    -0.06
    POSITIVE LOGITS
    AttributeValue
    0.07
    奶
    0.07
    ets
    0.06
    ModifiedDate
    0.06
     turno
    0.06
     content
    0.06
     involvement
    0.06
    afd
    0.06
    heimer
    0.06
     compared
    0.06
    Activations Density 0.076%

    No Known Activations