© 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. 59806
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation or sentence-ending markers

    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
     aut
    -0.06
    liner
    -0.06
    lh
    -0.06
    пÑĢа
    -0.05
    worthy
    -0.05
     Mueller
    -0.05
     warranted
    -0.05
    ynos
    -0.05
     Aut
    -0.05
    ç©
    -0.05
    POSITIVE LOGITS
    ooks
    0.07
    istické
    0.07
     Angiospermae
    0.07
    dfs
    0.07
     kaz
    0.07
    Dimension
    0.06
    ibo
    0.06
    ist
    0.06
    746
    0.06
    isci
    0.06
    Activations Density 0.000%

    No Known Activations