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. 78351
    Prev
    Next
    INDEX
    Explanations

    references to missile systems and related military terminology

    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
    avanaugh
    -0.07
    ulet
    -0.07
    istry
    -0.07
    ãģķãģ¾
    -0.07
    -widgets
    -0.07
    elijk
    -0.07
    vida
    -0.06
    ents
    -0.06
    ساÙĦ
    -0.06
     eleg
    -0.06
    POSITIVE LOGITS
    hower
    0.08
    ableObject
    0.07
     damp
    0.07
    atego
    0.07
    vů
    0.07
    vod
    0.07
    ábado
    0.06
     DataColumn
    0.06
    proof
    0.06
    /array
    0.06
    Activations Density 0.004%

    No Known Activations