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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96025
    Prev
    Next
    INDEX
    Explanations

    expressions related to horseback riding and equestrian activities

    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
    erah
    -0.08
    amerate
    -0.08
    ubits
    -0.07
    ÑĮе
    -0.07
    awai
    -0.07
    fell
    -0.07
    alous
    -0.07
    abus
    -0.07
    cents
    -0.07
    æĮģãģ¡
    -0.07
    POSITIVE LOGITS
    quin
    0.06
    SError
    0.06
    ibox
    0.06
    HTTPHeader
    0.06
     Getty
    0.06
    ιÏĥ
    0.06
    cket
    0.06
    oda
    0.05
     Moss
    0.05
     Riley
    0.05
    Activations Density 0.006%

    No Known Activations