© 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. 60001
    Prev
    Next
    INDEX
    Explanations

    terms related to mobile data usage and its effects

    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
     interp
    -0.08
    atform
    -0.07
    iв
    -0.07
     Ñĩином
    -0.07
     migrationBuilder
    -0.06
    à¥Ģà¤ķरण
    -0.06
    .partial
    -0.06
    aupt
    -0.06
    ebin
    -0.06
    ginas
    -0.06
    POSITIVE LOGITS
     usage
    0.08
     Usage
    0.07
    .usage
    0.07
    usch
    0.07
    Usage
    0.07
    Peak
    0.07
    edo
    0.06
     Fair
    0.06
    USAGE
    0.06
    usage
    0.06
    Activations Density 0.008%

    No Known Activations