© 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. 26861
    Prev
    Next
    INDEX
    Explanations

    place names, particularly states and cities

    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
    .sul
    -0.08
    /WebAPI
    -0.08
    aoke
    -0.07
    .UnitTesting
    -0.07
    èĬĿ
    -0.07
    infeld
    -0.07
    rang
    -0.07
    ovich
    -0.07
    FSIZE
    -0.07
     CONTRIBUTORS
    -0.07
    POSITIVE LOGITS
    ['__
    0.06
    awning
    0.06
     mock
    0.06
    iana
    0.06
    -based
    0.06
    UnderTest
    0.06
     coron
    0.06
     lean
    0.06
    TypeInfo
    0.06
    ysis
    0.05
    Activations Density 0.062%

    No Known Activations