© 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. 15949
    Prev
    Next
    INDEX
    Explanations

    specific nouns and terms related to social issues and interactions

    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
     Sexe
    -0.07
    /repository
    -0.07
    ÑĮе
    -0.07
    achi
    -0.07
     allied
    -0.06
    ¼
    -0.06
    oda
    -0.06
    ãģ¶
    -0.06
    /Form
    -0.06
     aktuellen
    -0.06
    POSITIVE LOGITS
     typical
    0.11
     generally
    0.09
    ä»»ä½ķ
    0.09
    Generally
    0.08
     any
    0.08
     usual
    0.08
    Typ
    0.08
    typ
    0.08
     typically
    0.08
     Generally
    0.07
    Activations Density 0.005%

    No Known Activations