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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96000
    Prev
    Next
    INDEX
    Explanations

    names of educational institutions and their associated programs or locations

    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
    aura
    -0.08
    aju
    -0.07
    efd
    -0.07
    leine
    -0.07
     vyj
    -0.07
    aç
    -0.07
    onica
    -0.07
    ÄĽt
    -0.07
    arios
    -0.06
    AMS
    -0.06
    POSITIVE LOGITS
     Fold
    0.06
    fold
    0.06
     folds
    0.06
     fold
    0.06
     Watkins
    0.06
    /resource
    0.05
    æĺ
    0.05
    ¼åIJĪ
    0.05
    -fold
    0.05
    ständ
    0.05
    Activations Density 0.043%

    No Known Activations