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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5402
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     (*((
    -0.07
     Shack
    -0.06
     coun
    -0.06
    ï
    -0.06
       
    -0.06
    087
    -0.06
    -uri
    -0.06
    ãĥ©ãĥĥãĤ¯
    -0.06
    inox
    -0.06
     Joi
    -0.06
    POSITIVE LOGITS
     neod
    0.07
    inki
    0.07
    igen
    0.07
     contacts
    0.06
    кÑĤÑĥ
    0.06
    alen
    0.06
     spatial
    0.06
    igit
    0.06
    enties
    0.06
    .addHandler
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.