© 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. 125525
    Prev
    Next
    INDEX
    Explanations

    details about accommodations and their features

    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
    ovny
    -0.07
    ocity
    -0.06
     addObserver
    -0.06
     associates
    -0.06
    arked
    -0.06
    kaar
    -0.06
     Gre
    -0.06
    ark
    -0.06
    arks
    -0.06
    esser
    -0.06
    POSITIVE LOGITS
     Zimbabwe
    0.07
     Nam
    0.07
     sinh
    0.07
     khung
    0.07
     commod
    0.07
    .EventType
    0.07
     Beled
    0.06
    ifa
    0.06
    ÙĬÙĥÙĬ
    0.06
    .paths
    0.06
    Activations Density 0.003%

    No Known Activations