© 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. 89564
    Prev
    Next
    INDEX
    Explanations

    terms related to magnetic fields and their properties in various contexts

    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
    inka
    -0.07
    ossible
    -0.07
    ptions
    -0.07
     pylint
    -0.06
    lage
    -0.06
    ctl
    -0.06
    rise
    -0.06
    νο
    -0.06
     fri
    -0.06
    inel
    -0.06
    POSITIVE LOGITS
    aticon
    0.06
    atum
    0.06
    åľŃ
    0.06
    -na
    0.06
    ity
    0.06
    /math
    0.06
     Personality
    0.06
    isoft
    0.06
     Calories
    0.06
    aran
    0.06
    Activations Density 0.008%

    No Known Activations