© 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. 130832
    Prev
    Next
    INDEX
    Explanations

    references to usage and installation instructions

    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
    ÅĽnie
    -0.07
    ÑĥÑĢÑģ
    -0.07
    uet
    -0.07
    ÙĪاء
    -0.07
    Ñĥнк
    -0.07
    lected
    -0.07
    akis
    -0.07
    ule
    -0.07
    uchen
    -0.07
    andro
    -0.07
    POSITIVE LOGITS
    ystone
    0.06
     $#
    0.06
    onse
    0.06
    USAGE
    0.06
    odel
    0.06
    (@(
    0.06
    urgence
    0.06
     bande
    0.06
     Loss
    0.05
    BLOCK
    0.05
    Activations Density 0.006%

    No Known Activations