© 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. 78815
    Prev
    Next
    INDEX
    Explanations

    themes related to the institution of marriage and its implications

    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
    echa
    -0.07
    èĦ
    -0.06
    PHA
    -0.06
     ((*
    -0.06
    /grpc
    -0.06
    ami
    -0.06
    nek
    -0.05
    ủ
    -0.05
    ict
    -0.05
    522
    -0.05
    POSITIVE LOGITS
    erness
    0.08
    eroon
    0.07
    riage
    0.07
    ermal
    0.07
    asser
    0.07
    CLR
    0.07
     dur
    0.07
     durable
    0.06
    ÑģÑĤÑĢой
    0.06
    roles
    0.06
    Activations Density 0.009%

    No Known Activations