© 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. 70709
    Prev
    Next
    INDEX
    Explanations

    terms related to multiple directional or bi-directional concepts

    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
    636
    -0.08
    idel
    -0.08
    ucker
    -0.08
    heits
    -0.08
    tingham
    -0.07
    ëĭµ
    -0.07
    224
    -0.07
    anik
    -0.07
    onya
    -0.07
    ugg
    -0.07
    POSITIVE LOGITS
     nature
    0.07
    AMA
    0.07
    ANGER
    0.06
     communication
    0.06
    aron
    0.06
     communications
    0.06
    nature
    0.06
    /single
    0.06
     Lol
    0.06
    lol
    0.06
    Activations Density 0.007%

    No Known Activations