Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126515
    Prev
    Next
    INDEX
    Explanations

    numerical data and references in academic texts

    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
    loth
    -0.07
     Dresden
    -0.06
    strate
    -0.06
    ULD
    -0.06
    hdr
    -0.06
    Dyn
    -0.06
     DAO
    -0.06
     predecess
    -0.06
    abar
    -0.06
    .scalablytyped
    -0.06
    POSITIVE LOGITS
    iera
    0.07
    ardon
    0.07
    avra
    0.06
    gt
    0.06
    oui
    0.06
    /views
    0.06
     push
    0.06
     Sap
    0.06
    ona
    0.06
    IEWS
    0.06
    Activations Density 0.003%

    No Known Activations