© 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. 90516
    Prev
    Next
    INDEX
    Explanations

    adjectives that express affection or endearment

    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
    ÃĹ↵↵
    -0.08
    ä¸Ģç§į
    -0.07
    ̣
    -0.07
    ields
    -0.07
    kontakte
    -0.07
    ısıt
    -0.07
    istrov
    -0.07
     çĨ
    -0.07
    ůležit
    -0.07
    633
    -0.07
    POSITIVE LOGITS
    ly
    0.07
    est
    0.07
     (?)
    0.07
    lest
    0.07
    lic
    0.07
    esty
    0.06
     unw
    0.06
     Ms
    0.06
    liest
    0.05
    JD
    0.05
    Activations Density 0.030%

    No Known Activations