Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95974
    Prev
    Next
    INDEX
    Explanations

    terms related to control and operation in systems or technology

    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
    uty
    -0.09
    PKG
    -0.07
    cle
    -0.07
    ugen
    -0.07
    icias
    -0.07
    ibil
    -0.07
    oris
    -0.07
    iverz
    -0.07
    uti
    -0.07
     forCellReuseIdentifier
    -0.07
    POSITIVE LOGITS
     controls
    0.07
    /control
    0.07
    -by
    0.06
    ECT
    0.06
     actionable
    0.06
    -control
    0.06
    ç°
    0.06
    EC
    0.06
    /command
    0.06
    actions
    0.06
    Activations Density 0.020%

    No Known Activations