© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 83749
    Prev
    Next
    INDEX
    Explanations

    references to ammunition specifications and usage

    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
    .scalablytyped
    -0.07
    sob
    -0.06
    urm
    -0.06
     Mesh
    -0.06
    973
    -0.06
    luk
    -0.06
     bik
    -0.06
     dysfunctional
    -0.06
    963
    -0.06
     пан
    -0.06
    POSITIVE LOGITS
    ÏĥÏĦο
    0.08
    Rocket
    0.08
    rocket
    0.08
     deton
    0.07
    Forge
    0.07
    avax
    0.07
     rocket
    0.07
    oggles
    0.07
    aghan
    0.07
     Rocket
    0.07
    Activations Density 0.005%

    No Known Activations