© 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. 60650
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and their associated context in text

    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
    aldi
    -0.07
    hazi
    -0.07
    orsk
    -0.07
    ikon
    -0.07
    nett
    -0.06
    cio
    -0.06
    iker
    -0.06
    iego
    -0.06
    allen
    -0.06
    ãĥ«ãĥī
    -0.06
    POSITIVE LOGITS
    ć
    0.06
    uis
    0.06
     Marino
    0.06
    ften
    0.06
    /cs
    0.06
     Leo
    0.05
    Ïģιν
    0.05
    etros
    0.05
    qrt
    0.05
     Lind
    0.05
    Activations Density 0.007%

    No Known Activations