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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 5148
    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
    aida
    -0.07
     rodin
    -0.06
    dao
    -0.06
     timelines
    -0.06
    offer
    -0.06
    rary
    -0.06
    enheim
    -0.06
    ende
    -0.06
    ahas
    -0.06
    oplan
    -0.06
    POSITIVE LOGITS
    OKIE
    0.08
     society
    0.07
     social
    0.07
    ÏĦαÏĤ
    0.06
    491
    0.06
     view
    0.06
     according
    0.06
     CHUNK
    0.06
    474
    0.06
     ÄĮes
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.