© 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. 118760
    Prev
    Next
    INDEX
    Explanations

    mentions of studies and research findings

    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
    .impl
    -0.06
    zá
    -0.06
    mir
    -0.06
    bec
    -0.06
     undergo
    -0.06
     Patent
    -0.06
    iren
    -0.06
    culo
    -0.06
    685
    -0.06
     thing
    -0.06
    POSITIVE LOGITS
     studies
    0.08
    dae
    0.07
    dsl
    0.07
    ç´
    0.07
    Studies
    0.07
    unj
    0.07
    FindBy
    0.07
    \Migration
    0.07
     Studies
    0.07
     Roh
    0.07
    Activations Density 0.031%

    No Known Activations