Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126299
    Prev
    Next
    INDEX
    Explanations

    terminologies related to medical conditions, particularly those affecting the urinary tract

    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
    ÄĽÅ¾
    -0.09
    erp
    -0.07
    AMESPACE
    -0.07
    ãģĹãģ
    -0.07
    IOD
    -0.07
    .synthetic
    -0.06
     ÙĨادÙĬ
    -0.06
    inger
    -0.06
    /Runtime
    -0.06
    .Restr
    -0.06
    POSITIVE LOGITS
     importantly
    0.06
    cpt
    0.06
     Magnet
    0.06
    oret
    0.06
    orem
    0.05
     dep
    0.05
    eck
    0.05
    _rng
    0.05
    933
    0.05
    MS
    0.05
    Activations Density 0.042%

    No Known Activations