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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 87513
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and configurations

    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
    ŀĭ
    -0.08
    ween
    -0.07
    sty
    -0.07
     gangbang
    -0.07
    efe
    -0.07
    quoi
    -0.07
    paque
    -0.07
    lingen
    -0.07
    ILON
    -0.07
    mania
    -0.07
    POSITIVE LOGITS
     default
    0.07
     Jeb
    0.07
     Méd
    0.06
     arbitrary
    0.06
     Glob
    0.06
    atz
    0.06
     Laf
    0.06
    rad
    0.06
     Ard
    0.06
    "default
    0.06
    Activations Density 0.044%

    No Known Activations