© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94113
    Prev
    Next
    INDEX
    Explanations

    elements related to professionalism and organizational structure

    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
    .pretty
    -0.08
    oyer
    -0.07
    iyat
    -0.07
    ãĤ¾
    -0.07
    âĢŀP
    -0.06
     dimensions
    -0.06
    виÑĤ
    -0.06
    TOTYPE
    -0.06
     Levi
    -0.06
    rene
    -0.06
    POSITIVE LOGITS
     abych
    0.07
     ourselves
    0.07
     our
    0.07
    ISOString
    0.07
    ÑĢовиÑĩ
    0.06
     nostra
    0.06
     Hentai
    0.06
     //////////////////////////////////////////////////////////////////////////
    0.06
    arel
    0.06
    odont
    0.06
    Activations Density 0.031%

    No Known Activations