© 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. 73222
    Prev
    Next
    INDEX
    Explanations

    keywords related to access modifiers in programming, specifically 'readonly' and 'final'

    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
    icamente
    -0.07
    ston
    -0.07
    xon
    -0.07
    iel
    -0.07
    iquement
    -0.07
    ory
    -0.06
    rick
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    uum
    -0.06
    itta
    -0.06
    POSITIVE LOGITS
     static
    0.08
     IMapper
    0.07
    ÑģÑĮ
    0.07
     int
    0.06
    .portal
    0.06
    ////////////////////////////////////////////////////////////////
    0.06
     astr
    0.06
    üstü
    0.06
    oulos
    0.06
    aphael
    0.06
    Activations Density 0.003%

    No Known Activations