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. 95760
    Prev
    Next
    INDEX
    Explanations

    JavaScript functions and event handlers related to user interactions

    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
     decomposition
    -0.07
     actionTypes
    -0.06
    ampo
    -0.06
     اÙĦخاص
    -0.06
    Calibri
    -0.06
    PT
    -0.06
    alamat
    -0.06
    амп
    -0.06
    à¹Ģà¸Ĭ
    -0.06
    ount
    -0.06
    POSITIVE LOGITS
    ehr
    0.07
    vÄĽt
    0.07
    hasOne
    0.07
    å±ķ
    0.07
    etric
    0.06
    alat
    0.06
    yne
    0.06
    #af
    0.06
    .foundation
    0.06
    #echo
    0.06
    Activations Density 0.128%

    No Known Activations