© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 4064
    Prev
    Next
    INDEX
    Explanations

    references to people and their roles or identities, especially in a social or political context

    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
    sic
    -0.08
    psc
    -0.07
     smr
    -0.06
    utura
    -0.06
    ltra
    -0.06
    maj
    -0.06
    orners
    -0.06
    ãĥ¼ãĥŀ
    -0.06
    uto
    -0.06
    eldo
    -0.06
    POSITIVE LOGITS
    lenÃŃ
    0.06
    ÄįÃŃ
    0.06
     ActiveForm
    0.06
    jump
    0.06
    adc
    0.06
    ültür
    0.06
    .gridColumn
    0.06
    â̦↵↵↵
    0.06
     dikke
    0.06
    باØŃ
    0.06
    Activations Density 0.217%

    No Known Activations