© 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. 93901
    Prev
    Next
    INDEX
    Explanations

    expressions related to self-awareness and introspection

    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
     META
    -0.06
    _EVAL
    -0.06
    ENSE
    -0.06
     ********************************************************
    -0.06
    rades
    -0.06
    iais
    -0.06
    atta
    -0.06
     destinationViewController
    -0.06
    Utc
    -0.06
    insky
    -0.06
    POSITIVE LOGITS
     already
    0.07
    ucks
    0.07
    ivan
    0.06
    umas
    0.06
    orno
    0.06
    fec
    0.06
    eyond
    0.06
     ÙĦÙħ
    0.06
    ož
    0.06
    rottle
    0.06
    Activations Density 0.021%

    No Known Activations