© 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. 57097
    Prev
    Next
    INDEX
    Explanations

    key phrases and themes relating to love and relationships

    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
    etto
    -0.09
    iyim
    -0.08
    ymi
    -0.08
    âķĿ
    -0.07
    skirts
    -0.07
    _caps
    -0.07
    dera
    -0.07
    nÄĽji
    -0.07
    é¹
    -0.07
     ì¶ľìŀ¥
    -0.07
    POSITIVE LOGITS
     met
    0.06
     become
    0.06
     Phelps
    0.06
     becomes
    0.06
    met
    0.06
    Met
    0.06
     Bernstein
    0.06
     co
    0.05
    aug
    0.05
    adh
    0.05
    Activations Density 0.017%

    No Known Activations