© 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. 15-LLAMASCOPE-RES-131K
    11. 88210
    Prev
    Next
    INDEX
    Explanations

    references to people involved in newsworthy incidents

    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
    faq
    -0.06
    ühr
    -0.06
     Kür
    -0.06
     fame
    -0.06
    loquent
    -0.06
    uth
    -0.06
     dens
    -0.06
    airro
    -0.06
     mod
    -0.06
    thing
    -0.06
    POSITIVE LOGITS
    gi
    0.08
    tiv
    0.07
    chl
    0.07
     Jr
    0.07
    odka
    0.06
    formace
    0.06
    acha
    0.06
    енÑĮ
    0.06
    roti
    0.06
    itore
    0.06
    Activations Density 0.011%

    No Known Activations