© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 78338
    Prev
    Next
    INDEX
    Explanations

    phrases indicating efforts to enhance local community well-being and education

    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
    ãĤ¤ãĤº
    -0.07
    ZN
    -0.06
    ä¼
    -0.06
    thern
    -0.06
     when
    -0.06
     if
    -0.06
    ácil
    -0.06
    emain
    -0.06
    omo
    -0.06
    ibu
    -0.06
    POSITIVE LOGITS
     awareness
    0.10
     Awareness
    0.09
     hol
    0.09
    aware
    0.08
     understanding
    0.08
    enda
    0.07
     Hol
    0.07
    tura
    0.07
    .getOwnProperty
    0.07
    ãĥķ
    0.07
    Activations Density 0.028%

    No Known Activations