© 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. 94602
    Prev
    Next
    INDEX
    Explanations

    elements related to simplicity and straightforwardness in processes or strategies

    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
    asca
    -0.07
     ÑĢаÑģк
    -0.06
    ITTE
    -0.06
    _CLIP
    -0.06
    prech
    -0.06
    aat
    -0.06
    751
    -0.06
    rát
    -0.06
    ocard
    -0.06
    reas
    -0.06
    POSITIVE LOGITS
    :
    0.07
     First
    0.06
    ausible
    0.06
     buy
    0.06
    ilon
    0.06
    ffi
    0.06
    anko
    0.06
    Ctrls
    0.06
    ala
    0.06
    grim
    0.06
    Activations Density 0.091%

    No Known Activations