© 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. 87585
    Prev
    Next
    INDEX
    Explanations

    specific references to places, concepts, and patterns in various contexts

    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
    ικο
    -0.07
    κοÏħ
    -0.07
    icana
    -0.07
    zano
    -0.07
    eview
    -0.06
     Brett
    -0.06
    Äįas
    -0.06
    629
    -0.06
    ÚĺÛĮ
    -0.06
    rng
    -0.06
    POSITIVE LOGITS
     itself
    0.10
     notoriously
    0.07
     tends
    0.07
    Fatal
    0.07
     Tier
    0.07
    DCF
    0.06
     tend
    0.06
    alcon
    0.06
     generally
    0.06
    being
    0.06
    Activations Density 0.031%

    No Known Activations