© 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. 5-LLAMASCOPE-RES-131K
    11. 126973
    Prev
    Next
    INDEX
    Explanations

    terms related to anti-conditions or anti-properties, particularly in health and physical contexts

    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
    _mA
    -0.07
    ÑĢÑı
    -0.06
    ildo
    -0.06
    usra
    -0.06
     sir
    -0.06
    å¸
    -0.06
     Vista
    -0.06
    çĭIJ
    -0.06
    ÑģÑĤвен
    -0.06
    åºŃ
    -0.06
    POSITIVE LOGITS
    Ĥ¬
    0.08
    oji
    0.07
    aten
    0.07
    yte
    0.07
    igh
    0.06
    reno
    0.06
    ater
    0.06
    aille
    0.06
    adık
    0.06
    icros
    0.06
    Activations Density 0.004%

    No Known Activations