© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 55261
    Prev
    Next
    INDEX
    Explanations

    references to action and surveillance within a tense narrative

    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
    رسÛĮ
    -0.08
    cház
    -0.07
    ubbo
    -0.07
     Cumhur
    -0.06
    íĥ
    -0.06
    prech
    -0.06
    undles
    -0.06
    æı®
    -0.06
    .getInteger
    -0.06
    ãĥ¡ãĥ©
    -0.06
    POSITIVE LOGITS
     Sil
    0.06
    vars
    0.06
    ops
    0.06
    now
    0.06
    MAC
    0.06
    audi
    0.05
     Counter
    0.05
    pline
    0.05
    okay
    0.05
     Brilliant
    0.05
    Activations Density 0.001%

    No Known Activations