© 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. 17-LLAMASCOPE-RES-131K
    11. 30646
    Prev
    Next
    INDEX
    Explanations

    phrases related to returning or coming back to a previous place

    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
    ãģķãģ¾
    -0.06
    rex
    -0.06
     ban
    -0.06
    нике
    -0.06
    ued
    -0.06
    yna
    -0.06
    FW
    -0.06
     fame
    -0.06
     Laud
    -0.05
    uce
    -0.05
    POSITIVE LOGITS
    PerPixel
    0.08
    iggins
    0.07
    ĵį
    0.07
    ahy
    0.07
    .nih
    0.07
    psilon
    0.07
    /themes
    0.07
    Å¡ov
    0.07
    summ
    0.07
    ุà¸ĩ
    0.07
    Activations Density 0.008%

    No Known Activations