© 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. 95725
    Prev
    Next
    INDEX
    Explanations

    terms related to financial dilution

    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
    ÅĻik
    -0.07
    TRANS
    -0.06
    .by
    -0.06
    foy
    -0.06
    allis
    -0.06
     éģĵ
    -0.06
    WARDED
    -0.06
    opal
    -0.06
    issen
    -0.06
     Ziel
    -0.06
    POSITIVE LOGITS
    ëŀĮ
    0.07
     whistle
    0.06
     pornstar
    0.06
     XPAR
    0.06
    edom
    0.06
    _cg
    0.06
    ODY
    0.06
    ERSHEY
    0.06
    ALA
    0.06
     *č↵
    0.06
    Activations Density 0.000%

    No Known Activations