© 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. 15-LLAMASCOPE-RES-131K
    11. 103841
    Prev
    Next
    INDEX
    Explanations

    phrases related to ritualistic practices and social constructs involving community, law, and moral standards

    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
    lead
    -0.06
    zl
    -0.06
    atus
    -0.06
    ori
    -0.06
     lead
    -0.06
    orr
    -0.06
     Wan
    -0.06
     skirts
    -0.05
     Steps
    -0.05
     Junk
    -0.05
    POSITIVE LOGITS
    avaÅŁ
    0.07
    bilder
    0.07
    ibling
    0.07
    _MetaData
    0.07
    elson
    0.07
    roadcast
    0.07
    InParameter
    0.07
    .LA
    0.06
    AdapterFactory
    0.06
    VarChar
    0.06
    Activations Density 0.027%

    No Known Activations