© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126617
    Prev
    Next
    INDEX
    Explanations

    coding keywords related to object-oriented programming

    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
    urai
    -0.08
    FIELDS
    -0.07
    _attached
    -0.07
    arov
    -0.07
    éal
    -0.07
    imedia
    -0.07
    ycz
    -0.07
     ÐŁÐ¾ÑģÑĤ
    -0.07
     ноÑĢ
    -0.07
    TouchUpInside
    -0.07
    POSITIVE LOGITS
    268
    0.08
    rame
    0.06
     Kum
    0.06
    allo
    0.06
    patibility
    0.06
    546
    0.05
    230
    0.05
     sun
    0.05
     stom
    0.05
     Vit
    0.05
    Activations Density 0.000%

    No Known Activations