© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89815
    Prev
    Next
    INDEX
    Explanations

    phrasing related to character experiences and emotional states

    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
     cave
    -0.06
    ave
    -0.06
     Fare
    -0.06
     readily
    -0.06
    uke
    -0.06
    etical
    -0.06
     cruc
    -0.06
    echa
    -0.06
    scratch
    -0.06
    erte
    -0.06
    POSITIVE LOGITS
     ÑĤепеÑĢ
    0.08
     ÑĤепеÑĢÑĮ
    0.08
    now
    0.08
     now
    0.08
     consequ
    0.08
    _now
    0.08
    ADIUS
    0.07
    piar
    0.07
    ewolf
    0.07
     Now
    0.07
    Activations Density 0.031%

    No Known Activations