© 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. 16364
    Prev
    Next
    INDEX
    Explanations

    references to specific organizational units or groups

    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
    nyder
    -0.07
    anoi
    -0.07
    ourn
    -0.06
    ãĥ³ãĥ
    -0.06
     vaz
    -0.06
    asted
    -0.06
    ongyang
    -0.06
    oro
    -0.06
    ifax
    -0.06
    anou
    -0.05
    POSITIVE LOGITS
     nearby
    0.08
    gateway
    0.07
    NSSet
    0.07
    erval
    0.07
    forge
    0.07
    /../
    0.07
     Nearby
    0.07
    Ī¬
    0.06
    ped
    0.06
    utm
    0.06
    Activations Density 0.000%

    No Known Activations