Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96003
    Prev
    Next
    INDEX
    Explanations

    elements associated with configuration options in a software context

    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
    abal
    -0.06
    ÅŁt
    -0.06
    /L
    -0.06
    fant
    -0.06
     imbalance
    -0.06
     sing
    -0.05
    vant
    -0.05
     compensate
    -0.05
     hopefully
    -0.05
    meler
    -0.05
    POSITIVE LOGITS
    ίνα
    0.09
    ÑĢÑĸд
    0.07
    ¯
    0.07
    à¹Īà¸Ńย
    0.07
    rve
    0.07
    /cop
    0.07
    æį·
    0.07
    ,cp
    0.07
    ëļ
    0.07
    оÑĢалÑĮ
    0.07
    Activations Density 0.008%

    No Known Activations