© 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. 76071
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly those that represent identification or classification

    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
    329
    -0.06
    åĬĽéĩı
    -0.06
    anky
    -0.06
    347
    -0.06
    707
    -0.06
    strict
    -0.06
    usi
    -0.05
    bern
    -0.05
    à¥ĩबस
    -0.05
    é¡
    -0.05
    POSITIVE LOGITS
    enger
    0.08
    aho
    0.08
    ostel
    0.07
    Ïħν
    0.07
    ounder
    0.07
    ANDOM
    0.07
     (*)(
    0.07
    olean
    0.07
    uards
    0.07
    mare
    0.06
    Activations Density 0.000%

    No Known Activations