© 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. 17-LLAMASCOPE-RES-131K
    11. 75578
    Prev
    Next
    INDEX
    Explanations

    words related to habitat and its characteristics

    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
    edom
    -0.07
    aims
    -0.06
    gos
    -0.06
    jišť
    -0.06
    /not
    -0.06
    enda
    -0.06
    imb
    -0.06
    ew
    -0.06
    edList
    -0.06
    uf
    -0.06
    POSITIVE LOGITS
    帯
    0.07
    abis
    0.07
    _lite
    0.07
    ÏĮ
    0.07
    etically
    0.07
    ted
    0.06
    /ec
    0.06
    ÎłÏģο
    0.06
    PickerController
    0.06
     conditions
    0.06
    Activations Density 0.005%

    No Known Activations