© 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. 15-LLAMASCOPE-RES-131K
    6. 88967
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "place to" followed by activities or 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
    pedo
    -0.08
    urv
    -0.07
    entai
    -0.07
    boom
    -0.07
    ssel
    -0.07
    inki
    -0.07
    iddi
    -0.07
    AWN
    -0.07
    idos
    -0.07
    awn
    -0.06
    POSITIVE LOGITS
    _defs
    0.06
    _PID
    0.06
    plex
    0.06
    اÙħÙĬ
    0.06
    .tr
    0.06
    zu
    0.06
     centrally
    0.06
    frog
    0.06
    adians
    0.06
    earned
    0.06
    Activations Density 0.008%

    No Known Activations