© 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. 77612
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their standings or actions within the context of elections

    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
    .scalablytyped
    -0.11
    -cols
    -0.08
    enko
    -0.08
    alta
    -0.08
    HeaderCode
    -0.07
     ФедеÑĢаÑĨии
    -0.07
    ä¸Ī
    -0.07
    _gc
    -0.07
    orex
    -0.07
    isol
    -0.07
    POSITIVE LOGITS
     candidates
    0.15
     candidate
    0.15
     Candidates
    0.12
     Candidate
    0.11
    Candidate
    0.11
    candidate
    0.10
     presidential
    0.10
    candidates
    0.10
    Candidates
    0.10
     campaign
    0.10
    Activations Density 0.292%

    No Known Activations