© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127695
    Prev
    Next
    INDEX
    Explanations

    references to Finnish architecture and architects

    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
    loth
    -0.08
     moci
    -0.07
     Ranch
    -0.07
    äch
    -0.07
    inic
    -0.06
    istrovstvÃŃ
    -0.06
    _LITERAL
    -0.06
    adic
    -0.06
    Äĥn
    -0.06
     Kaw
    -0.06
    POSITIVE LOGITS
     Finnish
    0.14
     Finland
    0.14
     Helsinki
    0.13
     Finn
    0.10
    .fi
    0.10
    onen
    0.10
     sauna
    0.10
    elsinki
    0.09
    ainen
    0.09
     Nokia
    0.09
    Activations Density 0.053%

    No Known Activations