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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 97702
    Prev
    Next
    INDEX
    Explanations

    code or programming-related terms and structures

    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
    âĢ¦I
    -0.06
    ivor
    -0.06
     Sat
    -0.06
    emouth
    -0.06
    ude
    -0.06
    .âĢ¦
    -0.06
     Christie
    -0.06
    avia
    -0.06
    ere
    -0.05
    addin
    -0.05
    POSITIVE LOGITS
     serm
    0.07
    Å®
    0.07
     cub
    0.07
    _FUNCTIONS
    0.07
    éĻµ
    0.07
     ÐĵÑĢи
    0.06
    ORMAL
    0.06
    ÑĨик
    0.06
    ubern
    0.06
    indir
    0.06
    Activations Density 0.032%

    No Known Activations