© 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. 17-LLAMASCOPE-RES-131K
    11. 58163
    Prev
    Next
    INDEX
    Explanations

    patterns or structures commonly associated with code or technical syntax

    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
    illac
    -0.07
    iglia
    -0.07
     Mach
    -0.07
    fsp
    -0.07
    jah
    -0.06
    úi
    -0.06
    _RCC
    -0.06
     Shank
    -0.06
    urma
    -0.06
    odom
    -0.06
    POSITIVE LOGITS
    Ñıз
    0.07
    ATUS
    0.07
     Bulk
    0.06
    xies
    0.06
    onden
    0.06
     sözleÅŁ
    0.06
    atus
    0.06
    озем
    0.06
     tslint
    0.05
    .selector
    0.05
    Activations Density 0.030%

    No Known Activations