© 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. 125713
    Prev
    Next
    INDEX
    Explanations

    numerical references or sequences related to data

    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
    Ú©ÙĨ
    -0.06
    enz
    -0.06
    ars
    -0.06
    ty
    -0.06
    rans
    -0.06
    PEC
    -0.06
    ized
    -0.06
     заклад
    -0.06
     afs
    -0.06
    _elim
    -0.06
    POSITIVE LOGITS
    adele
    0.07
    ednou
    0.07
    ë°©ìĨ¡
    0.07
    stringLiteral
    0.07
    obuf
    0.07
     Sadd
    0.07
    chartInstance
    0.07
    ombres
    0.06
    utenberg
    0.06
    aeper
    0.06
    Activations Density 0.008%

    No Known Activations