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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43757
    Prev
    Next
    INDEX
    Explanations

    phrases related to investigation and inquiry

    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
    ãĤĤãģªãģĦ
    -0.06
    аÑĤкÑĥ
    -0.06
    .trip
    -0.05
    á»Ļp
    -0.05
    /loose
    -0.05
    à¸IJาà¸Ļ
    -0.05
    ewith
    -0.05
    ÑĤÑĭй
    -0.05
    /single
    -0.05
    soever
    -0.05
    POSITIVE LOGITS
     whether
    0.30
     how
    0.30
     where
    0.27
     which
    0.27
     who
    0.27
     why
    0.23
     what
    0.22
     whom
    0.22
    whether
    0.21
     when
    0.21
    Activations Density 0.560%

    No Known Activations