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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 76288
    Prev
    Next
    INDEX
    Explanations

    references to various cultural contexts and values

    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
    aghan
    -0.07
    ëł
    -0.06
     kvin
    -0.06
     возÑĢаÑģÑĤа
    -0.06
    fon
    -0.06
    elson
    -0.06
    ÙħÙĪ
    -0.06
    pector
    -0.06
    gh
    -0.06
    aris
    -0.06
    POSITIVE LOGITS
     Westminster
    0.07
    ÙĬÙħÙĬ
    0.07
    iband
    0.06
    534
    0.06
     impunity
    0.06
     Learned
    0.06
    GetValue
    0.06
    .getOwnProperty
    0.06
     Contributors
    0.06
    kening
    0.06
    Activations Density 0.006%

    No Known Activations