© 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. 16098
    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
    mal
    -0.07
    rex
    -0.07
    372
    -0.07
    áce
    -0.07
    SORT
    -0.07
    POSIT
    -0.06
     simples
    -0.06
    839
    -0.06
    lan
    -0.06
    *pow
    -0.06
    POSITIVE LOGITS
    axe
    0.06
    ulumi
    0.06
    USA
    0.06
    侧
    0.06
    ypass
    0.06
     Mastery
    0.06
    elerik
    0.06
     Hao
    0.06
     bypass
    0.06
    izr
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.