© 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. 128613
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'incorporated' and related forms, indicating business or organizational 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
    maj
    -0.06
    nÄĽm
    -0.06
    à¤¿à¤ľ
    -0.06
     themed
    -0.06
    subscriptions
    -0.06
     hoe
    -0.06
    OLT
    -0.06
    themes
    -0.06
    èİ
    -0.06
     ÑģпÑĢав
    -0.06
    POSITIVE LOGITS
    hood
    0.06
    еÑģÑĤи
    0.06
     dissolve
    0.06
    ipple
    0.06
     Diss
    0.06
    /lic
    0.06
    aukee
    0.06
    -entity
    0.06
    STATUS
    0.06
     formation
    0.06
    Activations Density 0.003%

    No Known Activations