© 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. 984
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal memories and experiences

    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
     Mund
    -0.07
    gh
    -0.07
    iesel
    -0.06
    вен
    -0.06
    ymi
    -0.06
    eph
    -0.06
    ses
    -0.06
     Cousins
    -0.06
    abstractmethod
    -0.06
    eren
    -0.06
    POSITIVE LOGITS
     existence
    0.07
    090
    0.07
     Exist
    0.07
     ago
    0.07
    åŃĺåľ¨
    0.06
     exist
    0.06
    .Networking
    0.06
    istrovstvÃŃ
    0.06
     recru
    0.06
    upo
    0.06
    Activations Density 0.005%

    No Known Activations