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. 106724
    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
    éri
    -0.07
    eli
    -0.07
     generics
    -0.07
     PRIMARY
    -0.06
    aida
    -0.06
    iais
    -0.06
    aign
    -0.06
    åº
    -0.06
       
    -0.06
    rodu
    -0.06
    POSITIVE LOGITS
     shall
    0.06
     Shall
    0.06
     compact
    0.06
    /tos
    0.06
     Neh
    0.06
     Daly
    0.06
     aggreg
    0.06
     Broadcasting
    0.06
     Cla
    0.06
    jedn
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.