© 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. 79280
    Prev
    Next
    INDEX
    Explanations

    numerical data related to events or occurrences

    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
    KIT
    -0.08
    ItemAt
    -0.07
     ëĦ¤ìĿ´íĬ¸
    -0.07
    aload
    -0.07
    visa
    -0.07
     åıĮ线
    -0.07
     огÑĢа
    -0.07
    ÃĸL
    -0.07
    wind
    -0.07
    icer
    -0.07
    POSITIVE LOGITS
     Aqu
    0.07
     Masc
    0.06
    ion
    0.06
    779
    0.06
    alg
    0.06
    Aqu
    0.06
     Modifier
    0.05
    IEW
    0.05
     pan
    0.05
     aqu
    0.05
    Activations Density 0.001%

    No Known Activations