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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16682
    Prev
    Next
    INDEX
    Explanations

    concepts related to institutional structures or confinement

    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
     fitte
    -0.08
    rido
    -0.07
    _Insert
    -0.07
    _VALIDATE
    -0.07
    веÑī
    -0.06
    /../
    -0.06
    Calibri
    -0.06
    uen
    -0.06
     dán
    -0.06
     hete
    -0.06
    POSITIVE LOGITS
    -like
    0.14
    -esque
    0.09
     sorts
    0.08
    like
    0.08
    ÂĿ
    0.07
    _like
    0.07
     analogy
    0.07
    -style
    0.06
     virtual
    0.06
     Effect
    0.06
    Activations Density 0.082%

    No Known Activations