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. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43657
    Prev
    Next
    INDEX
    Explanations

    statistical data and metrics related to demographics and housing

    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
    osp
    -0.06
    lette
    -0.06
    andes
    -0.06
    ell
    -0.06
    olini
    -0.06
    otion
    -0.06
    InputLabel
    -0.06
    OSP
    -0.05
    linkplain
    -0.05
    ourmet
    -0.05
    POSITIVE LOGITS
     type
    0.11
     sex
    0.11
     selected
    0.09
     month
    0.09
     age
    0.09
     sexe
    0.09
     reason
    0.09
     mode
    0.09
     region
    0.09
     quart
    0.09
    Activations Density 0.008%

    No Known Activations