© 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 EvalsExportsinterp-engineNEWAPI 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. 73270
    Prev
    Next
    INDEX
    Explanations

    terms related to spiritual or mystical practices

    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
     Lon
    -0.06
    zung
    -0.06
     McMahon
    -0.06
    otor
    -0.06
    ror
    -0.06
     Chef
    -0.06
    ertz
    -0.05
    zano
    -0.05
    opp
    -0.05
    izard
    -0.05
    POSITIVE LOGITS
    heits
    0.07
    Intermediate
    0.07
    ctype
    0.07
    Joint
    0.07
    SCORE
    0.06
    ¢åįķ
    0.06
     tapped
    0.06
    ì§Ģ를
    0.06
     Fauc
    0.06
    urovision
    0.06
    Activations Density 0.021%

    No Known Activations