© 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. 126451
    Prev
    Next
    INDEX
    Explanations

    references to data structures and their relationships

    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
    InBackground
    -0.07
    ÑĥÑĤи
    -0.07
     umb
    -0.07
     denomin
    -0.07
    spa
    -0.07
     Ori
    -0.06
    uv
    -0.06
    /umd
    -0.06
    urtle
    -0.06
    umb
    -0.06
    POSITIVE LOGITS
    agina
    0.07
    ategy
    0.06
     nowhere
    0.06
    ULSE
    0.06
    mony
    0.06
     capita
    0.05
     whereabouts
    0.05
     billig
    0.05
    สà¸Ļ
    0.05
    Vi
    0.05
    Activations Density 0.008%

    No Known Activations