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. 106528
    Prev
    Next
    INDEX
    Explanations

    phrases related to service offerings and emotional connections

    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
    ayah
    -0.06
     (@
    -0.06
    /actions
    -0.06
     â
    -0.06
    (s
    -0.06
     Ãĥ
    -0.06
    IRECT
    -0.06
     (
    -0.06
     Directorate
    -0.06
    ãĢĤãĢĤ↵↵
    -0.06
    POSITIVE LOGITS
    اا
    0.07
    utherland
    0.07
     Erotische
    0.07
     způsobem
    0.06
    ango
    0.06
    engl
    0.06
     Gür
    0.06
    opoulos
    0.06
    InBackground
    0.06
    raud
    0.06
    Activations Density 0.001%

    No Known Activations