© 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. 105042
    Prev
    Next
    INDEX
    Explanations

    phrases related to costs and problems

    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
    undra
    -0.07
    _featured
    -0.07
    RITE
    -0.07
    /movie
    -0.07
    Äįe
    -0.06
    /embed
    -0.06
    ITOR
    -0.06
    ÏįÏĦε
    -0.06
     Piper
    -0.06
     trá»ĭ
    -0.06
    POSITIVE LOGITS
    /no
    0.08
    igu
    0.07
    uce
    0.07
     recipro
    0.07
    acas
    0.06
    ада
    0.06
    kker
    0.06
    /fast
    0.06
    oldem
    0.06
    igg
    0.06
    Activations Density 0.010%

    No Known Activations