© 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 EvalsExportsAPI 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. 77165
    Prev
    Next
    INDEX
    Explanations

    quantifiable mentions of groups or populations

    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
    _atual
    -0.09
    soever
    -0.08
    oksen
    -0.07
    asso
    -0.07
    å¼¾
    -0.07
    _estado
    -0.07
     undermin
    -0.07
    utsch
    -0.07
     fitte
    -0.06
    تاÙĨ
    -0.06
    POSITIVE LOGITS
     supporters
    0.07
     support
    0.07
     gathered
    0.06
     Supporting
    0.06
    acre
    0.06
     Supporters
    0.06
    erek
    0.06
     supports
    0.06
     representatives
    0.06
    Support
    0.06
    Activations Density 0.031%

    No Known Activations