© 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. 17-LLAMASCOPE-RES-131K
    11. 82351
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and parental figures

    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
    achen
    -0.08
    acher
    -0.07
    ynchronously
    -0.07
    exels
    -0.06
    BuilderInterface
    -0.06
    Animating
    -0.06
    volution
    -0.06
    eÄį
    -0.06
    chein
    -0.06
     Laden
    -0.06
    POSITIVE LOGITS
    ëģ
    0.06
     birthdays
    0.06
     gave
    0.06
    éĢģ
    0.06
     birthday
    0.06
     bulk
    0.06
     died
    0.06
    onds
    0.05
     Overse
    0.05
     gift
    0.05
    Activations Density 0.021%

    No Known Activations