© 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. 9-LLAMASCOPE-RES-131K
    11. 95507
    Prev
    Next
    INDEX
    Explanations

    references to cryptocurrencies and their investment potential

    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
    rror
    -0.08
    ependency
    -0.06
    oler
    -0.06
    ABCDEFGHIJKLMNOP
    -0.06
    ocode
    -0.06
     pylint
    -0.06
     Bakan
    -0.06
    oire
    -0.06
    lesc
    -0.06
    efault
    -0.06
    POSITIVE LOGITS
    preneur
    0.06
    ungeon
    0.06
    atat
    0.06
    ourcem
    0.06
    zym
    0.06
    basket
    0.06
    ë¦
    0.06
    mdb
    0.06
     вов
    0.05
     NG
    0.05
    Activations Density 0.005%

    No Known Activations