© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 75930
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempts and actions in technical contexts

    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
     or
    -0.07
     other
    -0.06
    tha
    -0.06
    884
    -0.06
    pun
    -0.06
    ely
    -0.06
     anderen
    -0.06
    lav
    -0.06
    ,
    -0.06
    ates
    -0.06
    POSITIVE LOGITS
    Certain
    0.09
    quential
    0.08
     Certain
    0.08
    .opendaylight
    0.07
    ÑĥÑĢа
    0.07
    InParameter
    0.07
    .experimental
    0.07
    WidgetItem
    0.07
     minha
    0.07
     certain
    0.07
    Activations Density 0.015%

    No Known Activations