© 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. 17-LLAMASCOPE-RES-131K
    11. 119393
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating possession or attributes

    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
    оÑĢон
    -0.07
     UnityEditor
    -0.07
    arters
    -0.07
    ammo
    -0.07
    arius
    -0.07
    ân
    -0.07
    .Css
    -0.07
    .exc
    -0.06
    éłĺ
    -0.06
     ëĵ¤
    -0.06
    POSITIVE LOGITS
     sorts
    0.10
     course
    0.10
    course
    0.09
    icina
    0.09
    -course
    0.09
    sted
    0.09
    ff
    0.09
    er
    0.08
    ewith
    0.07
    iciálnÃŃ
    0.07
    Activations Density 0.283%

    No Known Activations