© 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. 130770
    Prev
    Next
    INDEX
    Explanations

    references to documents or statements that outline forthcoming information or updates

    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
     own
    -0.06
     Leonard
    -0.06
    itters
    -0.06
     Ih
    -0.06
    bid
    -0.05
    isha
    -0.05
    ilia
    -0.05
    ria
    -0.05
    own
    -0.05
    ules
    -0.05
    POSITIVE LOGITS
    .Utc
    0.08
    PRESS
    0.08
    Äįan
    0.07
    TickCount
    0.07
    _pci
    0.07
    ertino
    0.07
    fak
    0.07
    ạn
    0.07
    _depend
    0.07
    /vnd
    0.07
    Activations Density 0.009%

    No Known Activations