© 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. 15-LLAMASCOPE-RES-131K
    11. 88850
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
    afone
    -0.07
    è¬
    -0.06
    èĻ
    -0.06
    rong
    -0.06
    chester
    -0.06
    frei
    -0.06
    stadt
    -0.06
    zan
    -0.06
     norge
    -0.06
    /ex
    -0.06
    POSITIVE LOGITS
     presentViewController
    0.07
    .compiler
    0.07
    heck
    0.07
    essa
    0.07
     Donovan
    0.07
    arro
    0.07
    ektiv
    0.06
    erap
    0.06
    اصÙĦ
    0.06
    ONTAL
    0.06
    Activations Density 0.000%

    No Known Activations