© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61657
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and their programs

    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
    ãĥ
    -0.06
     â̦↵↵
    -0.06
    ваÑĤ
    -0.06
     wikipedia
    -0.06
    .LayoutStyle
    -0.06
     Covenant
    -0.05
    oval
    -0.05
    举
    -0.05
     privilege
    -0.05
    çξ
    -0.05
    POSITIVE LOGITS
    strup
    0.07
    assin
    0.07
    ä¼ı
    0.07
    utzer
    0.07
    inaire
    0.07
    agem
    0.06
    /MPL
    0.06
    engin
    0.06
    iday
    0.06
    uber
    0.06
    Activations Density 0.023%

    No Known Activations