© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82592
    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
    cts
    -0.07
    erville
    -0.07
    èĩ£
    -0.07
     Britain
    -0.06
    orgen
    -0.06
    elves
    -0.06
    iland
    -0.06
    ов
    -0.06
     worldwide
    -0.06
     Britt
    -0.06
    POSITIVE LOGITS
    .appspot
    0.07
    ARAM
    0.07
    âij
    0.06
    idon
    0.06
    éĥİ
    0.06
     Truy
    0.06
     pylint
    0.06
    ulas
    0.06
    tings
    0.06
    Queryable
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.