© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 61612
    Prev
    Next
    INDEX
    Explanations

    references to cancer and associated risks

    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
    cri
    -0.07
    optera
    -0.07
    umu
    -0.07
    gart
    -0.07
    ç
    -0.06
    alfa
    -0.06
    meer
    -0.06
    ecko
    -0.06
    urtles
    -0.06
    gross
    -0.06
    POSITIVE LOGITS
     for
    0.07
    MemoryWarning
    0.07
    ãĥ¥ãĥ¼
    0.06
    ÑĥÑĩа
    0.06
    objs
    0.06
    adro
    0.06
     factors
    0.06
    ModelIndex
    0.06
    igy
    0.05
    erse
    0.05
    Activations Density 0.007%

    No Known Activations