© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 60954
    Prev
    Next
    INDEX
    Explanations

    language related to controversial topics and artistic expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Sweep
    -0.07
    .scalablytyped
    -0.07
     vals
    -0.07
    ghost
    -0.07
    feld
    -0.07
    olumn
    -0.07
    Muon
    -0.06
    |int
    -0.06
    zilla
    -0.06
    ãİ
    -0.06
    POSITIVE LOGITS
     anarch
    0.07
    .Direct
    0.07
     libert
    0.07
     Disorder
    0.06
     chaos
    0.06
    /libs
    0.06
    éľ²åĩº
    0.06
    PyObject
    0.06
     Liberties
    0.06
    CString
    0.06
    Activations Density 0.269%

    No Known Activations