© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1261
    Prev
    Next
    INDEX
    Explanations

    phrases related to appointments or official positions

    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
    jis
    -0.07
    ivet
    -0.07
     baiser
    -0.07
    анÑģ
    -0.06
    iger
    -0.06
    isclosed
    -0.06
    antan
    -0.06
    .gdx
    -0.06
    asco
    -0.06
     Cust
    -0.06
    POSITIVE LOGITS
    lü
    0.07
    ±
    0.07
     finally
    0.07
    uffer
    0.06
    ΩΣ
    0.06
    ç»Īäºİ
    0.06
    ª
    0.06
    Terminal
    0.06
    rypt
    0.06
    olatile
    0.06
    Activations Density 0.003%

    No Known Activations