© 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. 3798
    Prev
    Next
    INDEX
    Explanations

    words related to love and affection

    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
    vla
    -0.08
    ulk
    -0.08
    é¼
    -0.08
    кÑĥлÑı
    -0.08
     lesbienne
    -0.07
    .toast
    -0.07
    aux
    -0.07
    _trait
    -0.07
    ä¹
    -0.07
    è¦
    -0.07
    POSITIVE LOGITS
     quotation
    0.07
    hardt
    0.07
    809
    0.06
    kke
    0.06
    sie
    0.06
    ably
    0.05
    yne
    0.05
     Rolling
    0.05
    sten
    0.05
    oppins
    0.05
    Activations Density 0.024%

    No Known Activations