© 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. 17-LLAMASCOPE-RES-131K
    6. 128751
    Prev
    Next
    INDEX
    Explanations

    user interface elements related to layout and configuration in code

    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
    oogle
    -0.07
    han
    -0.07
    udio
    -0.07
    ahan
    -0.06
    NotSupportedException
    -0.06
    itesse
    -0.06
    nech
    -0.06
     ÑģвеÑĤ
    -0.06
    ults
    -0.06
    .pat
    -0.06
    POSITIVE LOGITS
     =
    0.07
    steller
    0.07
    emsp
    0.07
    legen
    0.06
    issy
    0.06
    encil
    0.06
     Altern
    0.06
    CLR
    0.06
    à¥ģश
    0.06
    ysz
    0.06
    Activations Density 0.011%

    No Known Activations