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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103713
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating ownership or association

    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
    ä¸Ī
    -0.08
     quits
    -0.07
     ÙħÙĨاس
    -0.07
    .intellij
    -0.07
    acades
    -0.07
    roperty
    -0.07
    ucher
    -0.07
     ÑģобÑĭ
    -0.07
    еÑĢÑĮ
    -0.06
     âĨĴ↵↵
    -0.06
    POSITIVE LOGITS
     ability
    0.10
     attempt
    0.09
     tendency
    0.08
     inability
    0.08
     role
    0.08
     attempts
    0.07
     manner
    0.07
     insistence
    0.07
     near
    0.07
     willingness
    0.07
    Activations Density 0.055%

    No Known Activations