© 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. 9-LLAMASCOPE-RES-131K
    11. 95064
    Prev
    Next
    INDEX
    Explanations

    references to academic studies and research centers

    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
     Fri
    -0.07
    çľī
    -0.07
    VILLE
    -0.07
    gue
    -0.07
     Blasio
    -0.06
    _factory
    -0.06
    ETCH
    -0.06
     fri
    -0.06
    irut
    -0.06
    aille
    -0.06
    POSITIVE LOGITS
    arella
    0.07
    obile
    0.07
    ove
    0.06
    tran
    0.06
    cco
    0.06
     McCart
    0.06
    ëıĮ
    0.06
     Idol
    0.06
    /global
    0.06
    monds
    0.06
    Activations Density 0.000%

    No Known Activations