© 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. 16164
    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
    arResult
    -0.06
    inis
    -0.06
    Âłje
    -0.06
     Trap
    -0.06
     seper
    -0.06
    (Source
    -0.06
    InSection
    -0.06
     å®
    -0.06
    ehler
    -0.06
     protector
    -0.06
    POSITIVE LOGITS
     acres
    0.07
     acre
    0.07
    ÑĪÑĤ
    0.07
     ÎľÎŃ
    0.06
     aftermath
    0.06
    Unnamed
    0.06
     SPDX
    0.06
    .tm
    0.06
    cum
    0.06
    ÑĢазÑĥ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.