© 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. 128836
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistical data

    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
    ses
    -0.07
    s
    -0.07
    ese
    -0.07
    aso
    -0.06
    ise
    -0.06
    ATTLE
    -0.05
     Gaz
    -0.05
    Č
    -0.05
    ampton
    -0.05
    son
    -0.05
    POSITIVE LOGITS
    omik
    0.07
    ylim
    0.07
    lemn
    0.07
     Damen
    0.07
    aling
    0.07
    yaw
    0.07
    HttpException
    0.07
    istické
    0.07
    IMIT
    0.07
    ardu
    0.07
    Activations Density 0.006%

    No Known Activations