© 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. 5-LLAMASCOPE-RES-131K
    11. 125632
    Prev
    Next
    INDEX
    Explanations

    references to limbs and their anatomical significance

    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
    eyn
    -0.08
    eated
    -0.07
    nock
    -0.07
    ibo
    -0.07
    ırak
    -0.07
    yas
    -0.06
    -ÑĤо
    -0.06
    iba
    -0.06
    AGMA
    -0.06
     اÙĦعÙħ
    -0.06
    POSITIVE LOGITS
    áng
    0.08
    urge
    0.07
    sterdam
    0.06
    geois
    0.06
     ?>'
    0.06
    crest
    0.06
    ستÙħ
    0.06
    owers
    0.06
    forme
    0.06
    lož
    0.06
    Activations Density 0.002%

    No Known Activations