© 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. 9-LLAMASCOPE-RES-131K
    11. 98461
    Prev
    Next
    INDEX
    Explanations

    references to further education and ongoing learning

    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
    rette
    -0.06
    stal
    -0.06
     Synd
    -0.06
    ầm
    -0.06
    retty
    -0.06
    kich
    -0.06
    /out
    -0.06
    ukan
    -0.06
    kh
    -0.05
    rames
    -0.05
    POSITIVE LOGITS
    780
    0.08
    FragmentManager
    0.07
    assel
    0.07
    証
    0.07
     Renders
    0.07
     arom
    0.07
    agara
    0.07
    enek
    0.07
    .rnn
    0.07
    пÑĢимеÑĢ
    0.07
    Activations Density 0.015%

    No Known Activations