© 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. 15-LLAMASCOPE-RES-131K
    11. 86862
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to studies

    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
    reon
    -0.07
    oron
    -0.07
    akis
    -0.07
    pering
    -0.07
    Swift
    -0.07
    teki
    -0.06
    phabet
    -0.06
     Bose
    -0.06
    ayne
    -0.06
    xea
    -0.06
    POSITIVE LOGITS
     eg
    0.06
     dispens
    0.06
    маÑħ
    0.06
    ele
    0.06
    yang
    0.05
    ç°
    0.05
     Hicks
    0.05
    anj
    0.05
    echan
    0.05
    /io
    0.05
    Activations Density 0.014%

    No Known Activations