© 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. 93744
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their titles

    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
    ën
    -0.07
    uming
    -0.07
    imli
    -0.07
    ãĥ¼ãĥĦ
    -0.07
    arya
    -0.07
    ůr
    -0.07
     männ
    -0.06
    quer
    -0.06
    sheet
    -0.06
    -generic
    -0.06
    POSITIVE LOGITS
    ial
    0.11
    -elect
    0.08
     cabinets
    0.07
    onas
    0.07
     Cabinets
    0.07
    IAL
    0.06
    erialization
    0.06
     cabinet
    0.06
    478
    0.06
    /top
    0.06
    Activations Density 0.005%

    No Known Activations