© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127880
    Prev
    Next
    INDEX
    Explanations

    references to the Apache organization and its related resources

    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
    ked
    -0.07
    xea
    -0.07
    reon
    -0.06
    vla
    -0.06
    yne
    -0.06
    ÑĢог
    -0.06
    phis
    -0.06
    acente
    -0.06
    orthy
    -0.06
    amm
    -0.06
    POSITIVE LOGITS
    .com
    0.08
    pole
    0.07
    ovich
    0.07
    ±
    0.07
    .org
    0.06
    ople
    0.06
    .dy
    0.06
    çĤİ
    0.06
    zilla
    0.06
    .edu
    0.06
    Activations Density 0.000%

    No Known Activations