© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97361
    Prev
    Next
    INDEX
    Explanations

    references to social connectivity and engagement

    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
    utherland
    -0.08
    ged
    -0.07
    @example
    -0.06
    -aged
    -0.06
    ueba
    -0.06
    evin
    -0.06
    ̣
    -0.06
    ut
    -0.06
    /al
    -0.06
     repe
    -0.06
    POSITIVE LOGITS
    atak
    0.07
     kav
    0.07
    locator
    0.06
    atin
    0.06
    «ĺ
    0.06
    acier
    0.06
    580
    0.06
    istrovstvÃŃ
    0.06
    BX
    0.06
    acre
    0.06
    Activations Density 0.003%

    No Known Activations