© 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. 15004
    Prev
    Next
    INDEX
    Explanations

    phrases that express beliefs or perspectives on creativity and individuality

    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
    kus
    -0.08
    俺ãģ¯
    -0.08
    egra
    -0.07
     bì
    -0.07
    maz
    -0.07
    DRV
    -0.07
     âĢı
    -0.07
    "struct
    -0.06
    âĻª
    -0.06
    íĥģ
    -0.06
    POSITIVE LOGITS
     or
    0.08
     æĪĸ
    0.07
    haps
    0.07
    æĪĸ
    0.07
    ãģ¾ãģŁãģ¯
    0.06
    (ed
    0.06
    باد
    0.06
    alic
    0.06
    ieval
    0.06
     communities
    0.06
    Activations Density 0.000%

    No Known Activations