Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5323
    Prev
    Next
    INDEX
    Explanations

    the name "Nik" and its variations

    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
    uire
    -0.07
    uit
    -0.07
    iger
    -0.07
    /umd
    -0.06
    acional
    -0.06
     Bracket
    -0.06
     Gim
    -0.06
    Opaque
    -0.06
    ÙĪØ§Øª
    -0.06
    aylight
    -0.06
    POSITIVE LOGITS
    hil
    0.08
    kke
    0.08
    las
    0.07
    s
    0.07
    ky
    0.07
    kor
    0.07
    ko
    0.07
    äºľ
    0.07
     Americas
    0.07
    duÄŁunu
    0.07
    Activations Density 0.002%

    No Known Activations