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. 96004
    Prev
    Next
    INDEX
    Explanations

    phrases related to being confined or restricted in space

    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
    ENA
    -0.07
    ondere
    -0.06
    ÙIJÙħ
    -0.06
    asu
    -0.06
    cul
    -0.06
    ouples
    -0.06
     styl
    -0.06
    awi
    -0.06
    à¸ģารà¸ķ
    -0.06
    ysl
    -0.06
    POSITIVE LOGITS
    rane
    0.07
    кÑĥÑĢ
    0.07
    onian
    0.06
    /home
    0.06
     closing
    0.06
    .XR
    0.06
     Ñįлек
    0.06
    loff
    0.06
     home
    0.06
    OD
    0.06
    Activations Density 0.016%

    No Known Activations