© 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. 17-LLAMASCOPE-RES-131K
    11. 78646
    Prev
    Next
    INDEX
    Explanations

    high-frequency terms related to specific organizations and topics

    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
    aly
    -0.07
    iles
    -0.06
    âĢ¦↵
    -0.06
    ean
    -0.06
    chan
    -0.05
    âĢ¦
    -0.05
     â
    -0.05
     [âĢ¦]↵
    -0.05
    icher
    -0.05
    eno
    -0.05
    POSITIVE LOGITS
    ipop
    0.08
     банкÑĥ
    0.07
    .createClass
    0.07
    ï¸
    0.07
    Ā
    0.07
    ائÙĤ
    0.07
     ÙĪاÙĨ
    0.07
    اÛĮد
    0.07
    eday
    0.07
    รà¸ģ
    0.07
    Activations Density 0.047%

    No Known Activations