© 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. 119033
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistics and estimates concerning health and medical topics

    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
    ylland
    -0.07
     automát
    -0.07
    mess
    -0.07
    .scalablytyped
    -0.07
    aille
    -0.06
    ald
    -0.06
    promise
    -0.06
    vince
    -0.06
     výj
    -0.06
    vrd
    -0.06
    POSITIVE LOGITS
     roughly
    0.09
     probable
    0.08
     probably
    0.08
     likely
    0.08
     approximately
    0.07
     possibly
    0.07
    ulin
    0.07
    rough
    0.07
     Possibly
    0.07
     overall
    0.07
    Activations Density 0.032%

    No Known Activations