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. 93811
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to legislative actions and organizational structures

    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
    IFORM
    -0.06
     kla
    -0.06
    ัà¸ĵà¸ij
    -0.06
    Descriptions
    -0.06
     pregn
    -0.06
    CLAIM
    -0.06
     suce
    -0.06
     is
    -0.06
    лини
    -0.06
    .om
    -0.06
    POSITIVE LOGITS
     Äijá»ģu
    0.08
    çļĨ
    0.07
     respectively
    0.07
    ãĤĪãģ³
    0.07
    åĿĩ
    0.07
    éĥ½ä¸į
    0.07
    ï¼Įéĥ½
    0.07
     olmak
    0.07
     ê·¸ë¦¬ê³ł
    0.07
    enses
    0.07
    Activations Density 0.110%

    No Known Activations