© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95369
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to physical manipulation and tension

    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
    icken
    -0.08
    \grid
    -0.07
    rael
    -0.07
    hea
    -0.07
    ë°ķ
    -0.07
    lands
    -0.07
     AttributeSet
    -0.07
    hips
    -0.06
    .consume
    -0.06
    utsch
    -0.06
    POSITIVE LOGITS
    ormsg
    0.06
    sert
    0.06
    308
    0.06
    atable
    0.06
    0.06
    &m
    0.06
    orney
    0.06
    anda
    0.06
     Petro
    0.06
    Ì
    0.06
    Activations Density 0.016%

    No Known Activations