© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118639
    Prev
    Next
    INDEX
    Explanations

    units of measurement related to distance

    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
    baum
    -0.07
    aju
    -0.07
    cai
    -0.06
    osu
    -0.06
    irs
    -0.06
    маз
    -0.06
    duit
    -0.06
     natural
    -0.06
    Ế
    -0.05
    رد
    -0.05
    POSITIVE LOGITS
    inke
    0.07
    ÄĻki
    0.06
    MBProgressHUD
    0.06
    chers
    0.06
    ManagedObjectContext
    0.06
    Å¡ÃŃ
    0.06
    è³Ģ
    0.06
    ruba
    0.06
     uranus
    0.06
    ágenes
    0.06
    Activations Density 0.000%

    No Known Activations