© 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. 41821
    Prev
    Next
    INDEX
    Explanations

    news related to the passing of notable figures

    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
    ajaran
    -0.07
    หาร
    -0.07
    ÅĽcie
    -0.06
     دÙģ
    -0.06
    åħ¥ãĤĮ
    -0.06
    ORS
    -0.06
    íĻĢ
    -0.06
    distinct
    -0.05
    avar
    -0.05
    zeich
    -0.05
    POSITIVE LOGITS
     full
    0.13
     real
    0.13
    full
    0.11
    real
    0.11
     name
    0.11
    -full
    0.10
    /full
    0.10
     formal
    0.10
     fullname
    0.10
     formally
    0.10
    Activations Density 0.079%

    No Known Activations