© 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. 86695
    Prev
    Next
    INDEX
    Explanations

    instances of the word "without" in relation to permissions and regulations

    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
    мм
    -0.07
    alink
    -0.07
    zelf
    -0.07
    ().'/
    -0.07
    .bunifuFlatButton
    -0.07
    æ®Ĭ
    -0.07
    éīĦ
    -0.07
    ffi
    -0.07
     дав
    -0.07
    chez
    -0.06
    POSITIVE LOGITS
    ieri
    0.07
    iani
    0.06
    .infinity
    0.06
    batis
    0.06
    ia
    0.06
    iers
    0.05
     Ced
    0.05
    é¡»
    0.05
    ialis
    0.05
    wner
    0.05
    Activations Density 0.001%

    No Known Activations