© 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. 17-LLAMASCOPE-RES-131K
    11. 40502
    Prev
    Next
    INDEX
    Explanations

    elements associated with community engagement and support initiatives

    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
    rase
    -0.08
    aska
    -0.07
    ully
    -0.07
    amba
    -0.07
    ÑĢив
    -0.07
    iÄįe
    -0.07
    ESCO
    -0.06
    AGMA
    -0.06
    инки
    -0.06
    loat
    -0.06
    POSITIVE LOGITS
    oyo
    0.08
     tang
    0.06
     Ali
    0.06
    ocaly
    0.06
     veto
    0.05
     Hd
    0.05
    ãĥĥãĥĦ
    0.05
    mite
    0.05
     Voy
    0.05
    ante
    0.05
    Activations Density 0.040%

    No Known Activations