© 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. 59479
    Prev
    Next
    INDEX
    Explanations

    references to interactions and connections in online content

    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
    ennai
    -0.07
    278
    -0.06
     Cunning
    -0.06
     Getty
    -0.06
    éĻµ
    -0.05
     Matth
    -0.05
     Boeh
    -0.05
    gart
    -0.05
     γλη
    -0.05
     beaut
    -0.05
    POSITIVE LOGITS
    æĸĩç«ł
    0.07
    ARA
    0.07
     article
    0.07
    -article
    0.06
    sı
    0.06
    ıb
    0.06
    ãĥ¼ãĥĦ
    0.06
    roj
    0.06
    ÏĦαι
    0.06
    pherical
    0.06
    Activations Density 0.001%

    No Known Activations