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. 9-LLAMASCOPE-RES-131K
    6. 95896
    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
    ZN
    -0.07
    ait
    -0.06
    itos
    -0.06
     pard
    -0.06
     Carp
    -0.06
    αιδ
    -0.06
    IELDS
    -0.06
    inois
    -0.06
     Tank
    -0.06
    IRMWARE
    -0.06
    POSITIVE LOGITS
    /xhtml
    0.08
    332
    0.07
    nost
    0.06
    aye
    0.06
     Lana
    0.06
    ayo
    0.06
    ãĥ¥
    0.06
     AndAlso
    0.06
    iola
    0.06
    δι
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.