© 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. 95459
    Prev
    Next
    INDEX
    Explanations

    expressions indicating contrast or exception

    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
    zin
    -0.07
    chw
    -0.07
    .mods
    -0.07
     ìŀĪëĭ¤ê³ł
    -0.07
     eÅŁ
    -0.07
    ebe
    -0.07
    ardin
    -0.07
    _deinit
    -0.06
    ibern
    -0.06
    Dic
    -0.06
    POSITIVE LOGITS
     *)((
    0.07
    OTT
    0.06
    ecta
    0.06
    ether
    0.06
    IDER
    0.06
    iner
    0.06
    IOD
    0.06
    anime
    0.06
    licted
    0.06
     Locke
    0.06
    Activations Density 0.029%

    No Known Activations