© 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. 61619
    Prev
    Next
    INDEX
    Explanations

    phrases related to new beginnings or arrivals

    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
    pga
    -0.08
    ucer
    -0.08
    ائر
    -0.07
    èĥĨ
    -0.07
    ä¿Ŀ
    -0.07
    rna
    -0.07
     kê
    -0.06
    izz
    -0.06
    hiba
    -0.06
    rios
    -0.06
    POSITIVE LOGITS
     adulthood
    0.07
     new
    0.07
    sing
    0.06
    960
    0.06
    igos
    0.06
    961
    0.06
    876
    0.06
     bring
    0.06
     forth
    0.06
     era
    0.06
    Activations Density 0.021%

    No Known Activations