© 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. 78947
    Prev
    Next
    INDEX
    Explanations

    references to inclusivity and access for various groups of people

    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
    ingly
    -0.07
    UNS
    -0.07
    azzi
    -0.07
    plural
    -0.07
    antan
    -0.06
    apiro
    -0.06
    blink
    -0.06
    nul
    -0.06
    aine
    -0.06
    illes
    -0.06
    POSITIVE LOGITS
    (er
    0.06
     races
    0.06
     Races
    0.06
    omaly
    0.06
    inode
    0.06
     Equal
    0.06
     equal
    0.06
    ANI
    0.06
    DAY
    0.06
     нÑĥж
    0.06
    Activations Density 0.011%

    No Known Activations