© 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. 88813
    Prev
    Next
    INDEX
    Explanations

    key actions related to launching and developing projects or initiatives

    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
     минÑĥ
    -0.08
    /Public
    -0.08
    /tos
    -0.08
    xDB
    -0.08
    atedRoute
    -0.08
    UFFIX
    -0.07
    =Value
    -0.07
    lád
    -0.07
    #${
    -0.07
    [from
    -0.07
    POSITIVE LOGITS
     called
    0.08
     "
    0.08
     named
    0.07
     '
    0.07
     entitled
    0.07
     titular
    0.07
     titled
    0.07
     `
    0.06
    :
    0.06
    misc
    0.06
    Activations Density 0.122%

    No Known Activations