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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-LLAMASCOPE-RES-131K
    6. 96093
    Prev
    Next
    INDEX
    Explanations

    themes related to environmentalism and nature

    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
    /apps
    -0.07
     Highest
    -0.06
    hift
    -0.06
    iore
    -0.06
    uche
    -0.06
    Dlg
    -0.06
    obb
    -0.06
     ActionTypes
    -0.06
     CGSizeMake
    -0.06
     ÑĢеÑĩ
    -0.06
    POSITIVE LOGITS
    gel
    0.07
     detail
    0.07
    ugen
    0.06
     pii
    0.06
     tuning
    0.06
     má»±c
    0.06
    WM
    0.06
     Daniels
    0.06
     Belg
    0.06
    utor
    0.06
    Activations Density 0.054%

    No Known Activations