© 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. 87612
    Prev
    Next
    INDEX
    Explanations

    HTML tags or elements related to formatting and structure in text

    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
    ite
    -0.07
    ihn
    -0.06
    pool
    -0.06
    own
    -0.06
    /Page
    -0.06
    ÃŃky
    -0.06
    ahu
    -0.06
    ppe
    -0.06
    leton
    -0.06
     Dess
    -0.06
    POSITIVE LOGITS
    uant
    0.07
     returnUrl
    0.07
    erdem
    0.06
    ensely
    0.06
    ï¸ı
    0.06
    iswa
    0.06
     Fletcher
    0.06
    ünd
    0.06
    âĶģ
    0.06
    SKI
    0.06
    Activations Density 0.011%

    No Known Activations