© 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. 17-LLAMASCOPE-RES-131K
    11. 17617
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and data 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
    newInstance
    -0.08
    _compiler
    -0.07
    veau
    -0.07
    STANCE
    -0.07
    alloca
    -0.07
    OrUpdate
    -0.07
    empo
    -0.07
    ãģ°ãģĭãĤĬ
    -0.07
     defaultManager
    -0.07
    pii
    -0.07
    POSITIVE LOGITS
     null
    0.07
     placebo
    0.07
     equivalent
    0.06
    null
    0.06
    acles
    0.06
    gro
    0.06
    ignal
    0.05
    è²´
    0.05
     Grund
    0.05
    gt
    0.05
    Activations Density 0.003%

    No Known Activations