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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 77878
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal activities and experiences

    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
     yola
    -0.08
    podob
    -0.08
    meden
    -0.07
    appe
    -0.07
    ráv
    -0.07
    asics
    -0.07
    gın
    -0.07
    _RESOURCES
    -0.07
    oggler
    -0.07
    Globals
    -0.07
    POSITIVE LOGITS
     twice
    0.09
     my
    0.07
     spent
    0.07
    Attempt
    0.06
     some
    0.06
     new
    0.06
    *
    0.06
     mostly
    0.06
     spend
    0.06
     myself
    0.06
    Activations Density 0.018%

    No Known Activations