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. 96103
    Prev
    Next
    INDEX
    Explanations

    names of relatives and family connections

    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
    obus
    -0.08
    asca
    -0.07
    efa
    -0.07
    ÑĤин
    -0.07
    aque
    -0.06
    arto
    -0.06
    IntPtr
    -0.06
    izedName
    -0.06
    que
    -0.06
    andas
    -0.06
    POSITIVE LOGITS
    .nih
    0.06
    ochen
    0.06
     Baron
    0.06
     éĩ
    0.06
     Prel
    0.06
    .method
    0.06
    ازÙĩ
    0.06
    ãĥ¼ãĤº
    0.06
    ãĥ¼ãĥŀ
    0.06
     clas
    0.06
    Activations Density 0.004%

    No Known Activations