© 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. 29621
    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
    din
    -0.08
    nodoc
    -0.07
    atorium
    -0.07
    Anchor
    -0.07
    itus
    -0.07
    cctor
    -0.07
    åĬ¨çĶŁæĪIJ
    -0.07
    ãĤ¤ãĥ³ãĥĪ
    -0.07
     DIN
    -0.07
    styleType
    -0.06
    POSITIVE LOGITS
    ä¾Ŀ
    0.06
    ogi
    0.06
    Ń
    0.06
    neau
    0.06
     McCabe
    0.06
     Klo
    0.06
     graz
    0.06
    IDER
    0.06
    ÙĦب
    0.06
    rag
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.