© 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. 17-LLAMASCOPE-RES-131K
    11. 95793
    Prev
    Next
    INDEX
    Explanations

    elements of social situations and interactions

    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
    óc
    -0.07
    irie
    -0.06
    çĴĥ
    -0.06
    isci
    -0.06
     سÙģ
    -0.06
    iasi
    -0.06
    ивÑĪи
    -0.06
    arto
    -0.06
    orman
    -0.06
    ocaly
    -0.06
    POSITIVE LOGITS
     public
    0.12
     everyone
    0.12
     Everyone
    0.11
     publicly
    0.11
     everybody
    0.11
    ä¼Ĺ
    0.10
    public
    0.10
    Everyone
    0.10
     público
    0.10
    .public
    0.10
    Activations Density 0.075%

    No Known Activations