© 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. 87163
    Prev
    Next
    INDEX
    Explanations

    symbols related to programming or code structure

    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
    moth
    -0.07
    innacle
    -0.07
    ema
    -0.07
    nis
    -0.07
    arel
    -0.06
    Mapped
    -0.06
     Klo
    -0.06
    orough
    -0.06
     Voll
    -0.06
    rung
    -0.06
    POSITIVE LOGITS
    uhn
    0.08
    .Lib
    0.07
    imson
    0.07
     sil
    0.07
    åľ°åŁŁ
    0.07
    hausen
    0.07
    ñana
    0.07
    ạt
    0.06
    Ùħا
    0.06
    pdata
    0.06
    Activations Density 0.002%

    No Known Activations