© 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. 15-LLAMASCOPE-RES-131K
    11. 88708
    Prev
    Next
    INDEX
    Explanations

    code structure and declarations within a programming context

    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
    823
    -0.07
    atch
    -0.07
    pher
    -0.06
     ÑĤеÑĩ
    -0.06
    .datas
    -0.06
    ront
    -0.06
    //@
    -0.06
    412
    -0.06
    821
    -0.06
    atten
    -0.06
    POSITIVE LOGITS
    orsche
    0.06
    tram
    0.06
    .PNG
    0.06
    leton
    0.06
    estructor
    0.06
    PURE
    0.06
    ividual
    0.06
    RetVal
    0.06
    regnum
    0.06
    ceipt
    0.05
    Activations Density 0.008%

    No Known Activations