© 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. 71696
    Prev
    Next
    INDEX
    Explanations

    instances of examples being referenced or used in a discussion

    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
    ì§ĢëıĦ
    -0.08
    евÑĭÑħ
    -0.06
    ature
    -0.06
    ugo
    -0.06
    ãģ¯ãģļ
    -0.06
    ulo
    -0.06
    ounce
    -0.06
    acz
    -0.06
    DataContract
    -0.06
     contests
    -0.06
    POSITIVE LOGITS
     example
    0.42
    example
    0.33
     Example
    0.33
     examples
    0.32
    Example
    0.30
     exemple
    0.30
    ä¾ĭ
    0.30
     ejemplo
    0.29
     exemplo
    0.29
    -example
    0.29
    Activations Density 0.093%

    No Known Activations