© 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. 56166
    Prev
    Next
    INDEX
    Explanations

    phrases related to non-commercial and private use

    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
    raÄį
    -0.07
    ades
    -0.06
    ormal
    -0.06
    :UIAlert
    -0.06
    rapped
    -0.06
    ori
    -0.06
    570
    -0.06
    470
    -0.05
    ionic
    -0.05
    arch
    -0.05
    POSITIVE LOGITS
     imper
    0.07
    gateway
    0.07
    iggs
    0.07
    omanip
    0.07
    yectos
    0.07
     Gate
    0.07
     -*-č↵
    0.07
    Sdk
    0.06
    htable
    0.06
    dech
    0.06
    Activations Density 0.001%

    No Known Activations