© 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. 87159
    Prev
    Next
    INDEX
    Explanations

    content related to video games, particularly updates and new features

    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
    atura
    -0.06
    edd
    -0.06
    ourke
    -0.06
    oplast
    -0.06
    оÑģп
    -0.06
    ata
    -0.06
     Opport
    -0.06
    ãĥĥãĤ¯ãĤ¹
    -0.06
    ANEL
    -0.06
    anel
    -0.06
    POSITIVE LOGITS
     Dost
    0.07
    ierz
    0.07
    __,↵
    0.07
    hil
    0.06
     Koreans
    0.06
    kich
    0.06
    icum
    0.06
    polygon
    0.06
    amu
    0.06
     sud
    0.06
    Activations Density 0.006%

    No Known Activations