© 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. 40156
    Prev
    Next
    INDEX
    Explanations

    HTML tags and structure related to forms and tables

    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
     ÙĤاÙĦب
    -0.07
    $core
    -0.07
    .BACK
    -0.07
    /*č↵
    -0.07
    etric
    -0.07
    EventData
    -0.07
    داÙħ
    -0.07
    	Copyright
    -0.06
    Ing
    -0.06
     ë°±
    -0.06
    POSITIVE LOGITS
     optional
    0.06
     Willis
    0.06
     hidden
    0.06
    div
    0.06
    onte
    0.06
    _hidden
    0.05
    ocaust
    0.05
    hidden
    0.05
    adders
    0.05
     patch
    0.05
    Activations Density 0.007%

    No Known Activations