© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28447
    Prev
    Next
    INDEX
    Explanations

    words related to the Asteraceae family of plants

    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
    alet
    -0.09
    ener
    -0.08
    sch
    -0.07
    /browser
    -0.07
    ÑĢоÑģÑĤ
    -0.07
    ató
    -0.07
    tae
    -0.07
    sim
    -0.07
    vil
    -0.07
    sko
    -0.07
    POSITIVE LOGITS
    lings
    0.10
    oids
    0.07
    дам
    0.07
    holm
    0.06
    dings
    0.06
    anlı
    0.06
    пов
    0.06
    нак
    0.06
    hap
    0.06
    head
    0.06
    Activations Density 0.009%

    No Known Activations