© 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. 87189
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to underrepresented or underserved communities and issues

    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
    /rfc
    -0.07
    amba
    -0.07
    ebi
    -0.07
    AZE
    -0.06
     é¡
    -0.06
    ABCDEFGHIJKLMNOP
    -0.06
    ónico
    -0.06
    ---</
    -0.06
    hiba
    -0.06
    olla
    -0.06
    POSITIVE LOGITS
     previously
    0.08
    eniable
    0.07
    apter
    0.07
    iles
    0.06
    ëŀĮ
    0.06
     Canter
    0.06
     dosud
    0.06
    oss
    0.06
    fragment
    0.06
    osu
    0.06
    Activations Density 0.017%

    No Known Activations