© 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. 60203
    Prev
    Next
    INDEX
    Explanations

    instances of certain special characters or diacritical marks

    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
    sou
    -0.07
    alue
    -0.07
    asio
    -0.07
    aran
    -0.07
    hand
    -0.07
    redo
    -0.06
    holm
    -0.06
    vre
    -0.06
    ãĥ¼ãĥĭ
    -0.06
    baugh
    -0.06
    POSITIVE LOGITS
    ning
    0.07
     Hammer
    0.06
    amp
    0.06
    ĭ
    0.06
     traceback
    0.06
    unkt
    0.06
    ampus
    0.06
    æ²Ļ
    0.06
    ç®±
    0.06
    _construct
    0.06
    Activations Density 0.002%

    No Known Activations