© 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. 15-LLAMASCOPE-RES-131K
    11. 61682
    Prev
    Next
    INDEX
    Explanations

    words and phrases that convey a sense of lament or sorrowful beauty

    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
    Äįást
    -0.06
     Quarry
    -0.06
    /goto
    -0.05
     shave
    -0.05
    Spl
    -0.05
     thicker
    -0.05
    άÏĤ
    -0.05
    é±
    -0.05
     dep
    -0.05
     relative
    -0.05
    POSITIVE LOGITS
    ugen
    0.07
    kir
    0.07
    ekil
    0.07
    gmail
    0.07
    redient
    0.07
    ATEGORIES
    0.06
    Ñģок
    0.06
    astos
    0.06
    º«
    0.06
    imest
    0.06
    Activations Density 0.001%

    No Known Activations