© 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. 15-LLAMASCOPE-RES-131K
    6. 90216
    Prev
    Next
    INDEX
    Explanations

    phrases expressing support and community involvement

    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
    _traits
    -0.07
    acen
    -0.07
    onth
    -0.07
    /welcome
    -0.07
    istrovstvÃŃ
    -0.06
     mourn
    -0.06
    UIAlertView
    -0.06
    trait
    -0.06
    ondo
    -0.06
    خرÛĮد
    -0.06
    POSITIVE LOGITS
    esel
    0.07
     Ñĥж
    0.07
    ç¯
    0.06
    ÎŃÏģα
    0.06
    ZF
    0.06
    ÑĨо
    0.06
    urum
    0.06
    лаÑĪ
    0.06
    pleted
    0.06
     Rig
    0.06
    Activations Density 0.008%

    No Known Activations