© 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. 15-LLAMASCOPE-RES-131K
    11. 86624
    Prev
    Next
    INDEX
    Explanations

    themes related to social issues and systemic challenges

    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
    vie
    -0.07
     Rencontre
    -0.06
    TZ
    -0.06
    гоÑĤ
    -0.06
    ifen
    -0.06
    adar
    -0.06
     realizing
    -0.06
    opa
    -0.06
    uchos
    -0.06
     branching
    -0.06
    POSITIVE LOGITS
    rof
    0.07
    ÅĻe
    0.07
     deeper
    0.07
     inheritance
    0.06
    emia
    0.06
    urf
    0.06
    bach
    0.06
     deep
    0.06
     transfer
    0.06
    eldon
    0.06
    Activations Density 0.046%

    No Known Activations