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. 43471
    Prev
    Next
    INDEX
    Explanations

    expressions of familial relationships and bonds

    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
    nonnull
    -0.07
    .dsl
    -0.06
     Erotische
    -0.06
    olit
    -0.06
    orum
    -0.06
    ÏĦοκ
    -0.06
     sez
    -0.06
    кÑĢеÑĤ
    -0.06
    PELL
    -0.06
    еÑĢб
    -0.06
    POSITIVE LOGITS
     family
    0.18
     FAMILY
    0.15
     extended
    0.14
     adopted
    0.14
     Family
    0.14
    family
    0.14
    -family
    0.14
     familia
    0.13
     familial
    0.13
     adoption
    0.12
    Activations Density 0.043%

    No Known Activations