© 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. 15-LLAMASCOPE-RES-131K
    11. 103887
    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
    chter
    -0.07
     seins
    -0.06
     er
    -0.06
     moderne
    -0.06
     vest
    -0.06
    ह
    -0.06
     dün
    -0.06
    주ìĿĺ
    -0.06
     kou
    -0.06
    uby
    -0.06
    POSITIVE LOGITS
    estone
    0.07
     Circular
    0.07
    ensburg
    0.07
    770
    0.07
    >\<^
    0.07
    çª
    0.06
    TextInput
    0.06
    leaf
    0.06
    oplast
    0.06
    eker
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.