© 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. 2300
    Prev
    Next
    INDEX
    Explanations

    terms related to solicitation and financial advisories

    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
    agen
    -0.07
    chg
    -0.07
    alez
    -0.07
     ÐŁÐ»Ð¾
    -0.07
    ibus
    -0.06
    ottie
    -0.06
    buster
    -0.06
    TEGER
    -0.06
    ockets
    -0.06
    iat
    -0.06
    POSITIVE LOGITS
     ÑĤол
    0.07
    cess
    0.06
    /Input
    0.06
    erk
    0.06
    ì±ħ
    0.06
     Sim
    0.06
    è£
    0.06
    _Utils
    0.06
     de
    0.05
     èª
    0.05
    Activations Density 0.000%

    No Known Activations