Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96221
    Prev
    Next
    INDEX
    Explanations

    instances of error messages or logs from software applications

    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
     nhau
    -0.07
    borg
    -0.07
    ocrates
    -0.06
    nu
    -0.06
    ónico
    -0.06
    /Typography
    -0.06
    oque
    -0.06
    anian
    -0.06
    /all
    -0.06
    jax
    -0.06
    POSITIVE LOGITS
    ISC
    0.07
    омеÑĢ
    0.07
    SSERT
    0.07
    ãĤ¡
    0.07
     Kens
    0.06
    ÏĨα
    0.06
    æĬµ
    0.06
    ãĥ«ãĥķ
    0.06
    ableObject
    0.06
     Dün
    0.06
    Activations Density 0.000%

    No Known Activations