© 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. 118221
    Prev
    Next
    INDEX
    Explanations

    locations or geographical references

    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
     Budget
    -0.07
    znám
    -0.07
     budget
    -0.07
    addock
    -0.06
     Marketable
    -0.06
    -budget
    -0.06
    addon
    -0.06
    bao
    -0.06
    postalcode
    -0.06
    ÑıÑĤи
    -0.06
    POSITIVE LOGITS
    /***/
    0.06
    ô
    0.06
    allo
    0.06
    983
    0.06
    ondo
    0.06
     flush
    0.06
    extras
    0.06
    ore
    0.06
     nich
    0.06
    ou
    0.05
    Activations Density 0.000%

    No Known Activations