© 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. 87418
    Prev
    Next
    INDEX
    Explanations

    hyperlinks in HTML documents

    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
    HBoxLayout
    -0.07
    á»ĭch
    -0.07
    ARS
    -0.07
    .scalablytyped
    -0.06
    etes
    -0.06
    akash
    -0.06
    NIC
    -0.06
    ét
    -0.06
     NavParams
    -0.06
    @Setter
    -0.06
    POSITIVE LOGITS
    Https
    0.06
    rial
    0.06
     Kron
    0.06
    0.06
    enever
    0.06
    inaire
    0.06
    #
    0.06
     Covered
    0.06
    uper
    0.06
    ÄĻki
    0.06
    Activations Density 0.004%

    No Known Activations