© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125509
    Prev
    Next
    INDEX
    Explanations

    alternatives or options in various contexts

    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
    aylight
    -0.09
    empo
    -0.09
    oldem
    -0.08
    ï¼Ĩ
    -0.08
    аниÑĨ
    -0.08
    вок
    -0.08
    ikan
    -0.08
    ваÑı
    -0.08
    ounter
    -0.08
    utzer
    -0.08
    POSITIVE LOGITS
    /or
    0.14
    phans
    0.12
    ifice
    0.10
     indeed
    0.10
     even
    0.09
     perhaps
    0.09
     maybe
    0.09
    lando
    0.09
    acular
    0.08
     else
    0.08
    Activations Density 0.232%

    No Known Activations