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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77108
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Chand" and variations of it

    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
    ading
    -0.07
    ursal
    -0.07
    uesto
    -0.07
     sca
    -0.07
    omba
    -0.07
    getSingleton
    -0.06
    adle
    -0.06
    алеж
    -0.06
    dings
    -0.06
    chest
    -0.06
    POSITIVE LOGITS
    wick
    0.09
    ammen
    0.07
    arkan
    0.07
    عات
    0.07
    rase
    0.07
    MLE
    0.07
    اص
    0.07
    amel
    0.07
    oler
    0.07
    rix
    0.07
    Activations Density 0.003%

    No Known Activations