© 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. 1420
    Prev
    Next
    INDEX
    Explanations

    references to blood and its various implications or contexts

    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
    -0.07
     âĨij
    -0.06
     selection
    -0.06
     Selection
    -0.06
    185
    -0.06
    inkle
    -0.06
     dere
    -0.06
     development
    -0.05
     Son
    -0.05
     (
    -0.05
    POSITIVE LOGITS
    .mvp
    0.08
    YGON
    0.08
    ynom
    0.07
    ied
    0.07
    ycop
    0.07
    -covered
    0.07
    avenport
    0.07
    _MACHINE
    0.07
    atoon
    0.07
    YN
    0.07
    Activations Density 0.022%

    No Known Activations