© 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. 130602
    Prev
    Next
    INDEX
    Explanations

    numeric information and related symbols

    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
    /REC
    -0.08
    barang
    -0.07
    ãĥ¤
    -0.07
    itten
    -0.07
     kostenlose
    -0.07
    Ú©Ø´
    -0.07
    dere
    -0.07
    ymi
    -0.07
    isay
    -0.07
    ượt
    -0.07
    POSITIVE LOGITS
    agus
    0.07
    urm
    0.06
    acio
    0.06
    igate
    0.06
     Guardian
    0.06
    wayne
    0.05
    ĵĺ
    0.05
     guard
    0.05
    ix
    0.05
     leaf
    0.05
    Activations Density 0.004%

    No Known Activations