© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124831
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating measurements or parameters in 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
    práv
    -0.07
    ecta
    -0.06
    ãĥ¼ãĥĦ
    -0.06
    lik
    -0.06
     dán
    -0.06
    avs
    -0.06
    dea
    -0.06
    ©
    -0.06
    TypeEnum
    -0.06
    othy
    -0.06
    POSITIVE LOGITS
    ÅĽci
    0.07
    250
    0.07
    igham
    0.07
    uled
    0.07
    Periph
    0.06
    ATA
    0.06
    ç¡
    0.06
    Uvs
    0.06
    )((((
    0.06
    500
    0.06
    Activations Density 0.052%

    No Known Activations