© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 90512
    Prev
    Next
    INDEX
    Explanations

    HTML input element types and attributes

    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
    -0.08
    otec
    -0.07
    ivant
    -0.07
     Edgar
    -0.06
    ibri
    -0.06
    utz
    -0.06
    ruz
    -0.06
     corner
    -0.06
     Livingston
    -0.06
    oku
    -0.06
    POSITIVE LOGITS
     Gloss
    0.07
    644
    0.06
     Animalia
    0.06
    Msp
    0.06
    AXB
    0.06
    640
    0.06
    沿
    0.06
    æŃ
    0.06
    ìĥ
    0.06
    ãĥ¼ãĥį
    0.06
    Activations Density 0.003%

    No Known Activations