© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 106382
    Prev
    Next
    INDEX
    Explanations

    the word "much" in various contexts to indicate emphasis or quantity

    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
    \controllers
    -0.07
    ziel
    -0.06
     sharper
    -0.06
    ess
    -0.06
    stackpath
    -0.06
    uff
    -0.06
    wood
    -0.06
    lock
    -0.06
    eler
    -0.06
    ŀĭ
    -0.06
    POSITIVE LOGITS
     more
    0.10
     более
    0.08
    more
    0.08
     più
    0.07
     less
    0.07
    viar
    0.07
     más
    0.07
    Globals
    0.07
    ibil
    0.07
    imately
    0.07
    Activations Density 0.021%

    No Known Activations