© 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 EvalsExportsinterp-engineNEWAPI 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. 61988
    Prev
    Next
    INDEX
    Explanations

    terms related to homelessness and its complexities

    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
    лаÑĪ
    -0.07
    ulta
    -0.07
    ÅŁk
    -0.07
    ç©
    -0.07
    Â
    -0.07
     malé
    -0.07
    672
    -0.07
     nesta
    -0.07
    nga
    -0.07
    ulan
    -0.07
    POSITIVE LOGITS
     etc
    0.08
     likewise
    0.08
    ãĥ¼ãĥĬ
    0.07
     finally
    0.07
     Finally
    0.07
     ÑĤоÑīо
    0.07
     And
    0.07
     dit
    0.06
    ucz
    0.06
    finally
    0.06
    Activations Density 0.110%

    No Known Activations