© 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. 17-LLAMASCOPE-RES-131K
    11. 93639
    Prev
    Next
    INDEX
    Explanations

    structural elements and organization within documents

    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
    hei
    -0.07
    asy
    -0.06
    úsqueda
    -0.06
     spons
    -0.06
    Boom
    -0.06
    icip
    -0.06
    .nlm
    -0.06
    shared
    -0.06
    ielding
    -0.06
     compart
    -0.06
    POSITIVE LOGITS
    .mi
    0.06
    à¤Łà¤°
    0.06
    æµľ
    0.06
     papers
    0.06
     Sommer
    0.06
    _minimum
    0.06
    jabi
    0.06
     Formation
    0.06
    åħį
    0.06
    è£ı
    0.06
    Activations Density 0.003%

    No Known Activations