© 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. 9-LLAMASCOPE-RES-131K
    11. 97358
    Prev
    Next
    INDEX
    Explanations

    structures and dimensions related to physical spaces or architectural features

    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
    ä¼
    -0.07
    irection
    -0.07
    çĤī
    -0.07
    енÑĮÑİ
    -0.07
    änge
    -0.06
    ubern
    -0.06
    angi
    -0.06
    629
    -0.06
    feld
    -0.06
    _mB
    -0.06
    POSITIVE LOGITS
    ToJson
    0.06
     inté
    0.06
     Town
    0.06
    aan
    0.06
    itoris
    0.06
    ÙĤÙĬØ©
    0.06
    apps
    0.06
    lick
    0.06
    /about
    0.06
     Hizmetleri
    0.05
    Activations Density 0.002%

    No Known Activations