© 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. 104274
    Prev
    Next
    INDEX
    Explanations

    references to equations and mathematical expressions

    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
    engin
    -0.07
    rella
    -0.06
    Ñıж
    -0.06
    alim
    -0.06
    ping
    -0.06
    rtle
    -0.06
    STAR
    -0.06
    ICLE
    -0.06
    elts
    -0.06
    rael
    -0.06
    POSITIVE LOGITS
    è©ŀ
    0.07
    _acquire
    0.06
    abcdefghijklmnop
    0.06
    anlı
    0.06
    urst
    0.06
    _Stream
    0.06
     åŀ
    0.06
    çĢ¬
    0.06
    ĥĿ
    0.06
    ä¸Ī
    0.06
    Activations Density 0.001%

    No Known Activations