© 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. 94075
    Prev
    Next
    INDEX
    Explanations

    phrases indicating physical positioning or actions related to visibility

    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
    ohon
    -0.07
    olare
    -0.07
    uant
    -0.07
    elp
    -0.06
    \Mapping
    -0.06
    bury
    -0.06
    elsen
    -0.06
     self
    -0.06
    ierz
    -0.06
    nave
    -0.06
    POSITIVE LOGITS
     window
    0.07
    TextChanged
    0.07
     ventana
    0.07
    Slot
    0.07
    Enumerator
    0.07
    éĢı
    0.07
    Window
    0.07
     Window
    0.07
    Restricted
    0.07
    window
    0.07
    Activations Density 0.021%

    No Known Activations