© 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. 4609
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the availability or sale of products or services

    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
    767
    -0.07
    PickerController
    -0.07
    oth
    -0.07
    299
    -0.07
    umber
    -0.07
    ůl
    -0.07
    isure
    -0.07
    /WebAPI
    -0.07
    .masks
    -0.07
    berger
    -0.07
    POSITIVE LOGITS
    vůli
    0.07
    eras
    0.07
    æĽ
    0.06
     Hol
    0.06
    0.06
    ãģijãģ©
    0.06
     nid
    0.06
    rik
    0.06
    ring
    0.05
     complete
    0.05
    Activations Density 0.039%

    No Known Activations