© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 118819
    Prev
    Next
    INDEX
    Explanations

    themes of communication and connection between individuals

    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
    اÙĪر
    -0.07
    nun
    -0.07
    inx
    -0.07
    _DIV
    -0.07
    CES
    -0.07
    _EXCEPTION
    -0.07
    ãĥĸ
    -0.07
    alph
    -0.06
    ernes
    -0.06
    íķĺìĭł
    -0.06
    POSITIVE LOGITS
     fellow
    0.13
    åIJĮ
    0.09
     peers
    0.09
     brethren
    0.09
     kin
    0.09
    ellow
    0.08
     Fellow
    0.08
     türü
    0.08
     species
    0.07
     fellows
    0.07
    Activations Density 0.068%

    No Known Activations