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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126567
    Prev
    Next
    INDEX
    Explanations

    references to sensors and sensing technologies

    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
    vos
    -0.08
    _Tis
    -0.08
    ajas
    -0.08
     /*č↵
    -0.07
    :UITableView
    -0.07
    uchar
    -0.07
    λη
    -0.07
    urnal
    -0.07
    orts
    -0.07
    osition
    -0.07
    POSITIVE LOGITS
     _
    0.06
    978
    0.06
     fab
    0.06
     apt
    0.06
    185
    0.05
     Fab
    0.05
    bai
    0.05
     Lonely
    0.05
     Gree
    0.05
    fab
    0.05
    Activations Density 0.007%

    No Known Activations