© 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. 15-LLAMASCOPE-RES-131K
    11. 90061
    Prev
    Next
    INDEX
    Explanations

    references to package management and installation commands in a Unix-like operating system

    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
    ži
    -0.07
    etes
    -0.06
    ects
    -0.06
    atır
    -0.06
     kou
    -0.06
    ets
    -0.06
    ñas
    -0.06
     Svens
    -0.06
    ensch
    -0.06
     sexuales
    -0.06
    POSITIVE LOGITS
    utter
    0.07
    ignore
    0.07
    ombo
    0.07
    owski
    0.07
    itude
    0.07
    itan
    0.07
     Pending
    0.07
    acer
    0.06
     Daddy
    0.06
    esser
    0.06
    Activations Density 0.001%

    No Known Activations