© 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. 17-LLAMASCOPE-RES-131K
    11. 69858
    Prev
    Next
    INDEX
    Explanations

    formal expressions or phrases related to definitions and explanations

    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
    ÑĦÑĦ
    -0.08
    оÑı
    -0.08
    èĶ
    -0.07
    $__
    -0.07
     kred
    -0.07
    laz
    -0.07
    ácil
    -0.07
    OMPI
    -0.07
     #__
    -0.07
    tae
    -0.07
    POSITIVE LOGITS
    ien
    0.06
    cente
    0.06
    amus
    0.06
    ahan
    0.06
    ilateral
    0.06
    amura
    0.06
    vid
    0.06
    nu
    0.05
    enario
    0.05
    utan
    0.05
    Activations Density 0.287%

    No Known Activations