© 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. 5-LLAMASCOPE-RES-131K
    11. 126610
    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
    vek
    -0.07
    ungs
    -0.07
    osate
    -0.07
    ADDE
    -0.07
    kinci
    -0.07
    avage
    -0.06
    ấm
    -0.06
    @student
    -0.06
    oplevel
    -0.06
     Holl
    -0.06
    POSITIVE LOGITS
    quete
    0.07
    éd
    0.06
    247
    0.06
    ieu
    0.06
     Cave
    0.06
    xia
    0.06
    otts
    0.06
     Cumhuriyet
    0.05
    911
    0.05
     denominator
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.