© 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. 62256
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific numeric values or symbols

    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
    /static
    -0.07
    etCode
    -0.06
     Poor
    -0.06
    .Static
    -0.06
    à¸Ľà¸£
    -0.06
     surname
    -0.06
    xb
    -0.05
    .static
    -0.05
    xB
    -0.05
     Settlement
    -0.05
    POSITIVE LOGITS
    ihan
    0.07
    stellung
    0.07
    Aligned
    0.06
    _attrib
    0.06
    ãĤ±ãĥ¼ãĤ¹
    0.06
     Hass
    0.06
     UPLOAD
    0.06
    stÃŃ
    0.06
    иÑģлов
    0.06
    dio
    0.06
    Activations Density 0.014%

    No Known Activations