© 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. 59240
    Prev
    Next
    INDEX
    Explanations

    phrases or constructions indicating possession or affiliation

    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
    ish
    -0.07
    ella
    -0.07
    eldon
    -0.07
     rencont
    -0.07
    enga
    -0.07
    çļĦæĺ¯
    -0.07
     Enc
    -0.06
    اجر
    -0.06
    eness
    -0.06
     ÑģлÑĥÑħ
    -0.06
    POSITIVE LOGITS
    igator
    0.08
    readcr
    0.07
    /all
    0.07
    awi
    0.07
    tern
    0.07
    usions
    0.06
     Canter
    0.06
    udden
    0.06
    PRECATED
    0.06
     sudden
    0.06
    Activations Density 0.022%

    No Known Activations