© 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. 126598
    Prev
    Next
    INDEX
    Explanations

    terms and phrases that indicate social recognition and connections among people

    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
    tering
    -0.07
    atego
    -0.07
    ãĥ¼ãĥ
    -0.07
    asz
    -0.07
    kowski
    -0.07
    chin
    -0.06
    edin
    -0.06
     quoi
    -0.06
    amespace
    -0.06
    kami
    -0.06
    POSITIVE LOGITS
     sebagai
    0.08
     as
    0.08
     каÑĩеÑģÑĤве
    0.07
    éry
    0.07
     kao
    0.06
     by
    0.06
    como
    0.06
     ÏīÏĤ
    0.06
     ìĿĺíķ´
    0.06
    ownt
    0.06
    Activations Density 0.017%

    No Known Activations