Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. MLP Out
    5. 29-LLAMASCOPE-MLP-131K
    6. 5081
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "Pro" suggesting a focus on professional or proactive themes

    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
    ered
    -0.06
    ament
    -0.06
    au
    -0.06
    ori
    -0.06
     true
    -0.06
    aci
    -0.05
    ure
    -0.05
     
    -0.05
     um
    -0.05
     ÑģпÑĢав
    -0.05
    POSITIVE LOGITS
    stitution
    0.08
    xima
    0.08
    phia
    0.08
    ustos
    0.08
    'gc
    0.07
    лек
    0.07
    _identity
    0.07
    IOD
    0.07
    tober
    0.07
    _firestore
    0.07
    Activations Density 0.015%

    No Known Activations