© 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. 15122
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual's name, 'Anne,' across various contexts

    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
    наÑĢ
    -0.06
    ÄĽÅ¾
    -0.06
    .PLL
    -0.06
    leftJoin
    -0.06
    @nate
    -0.06
    nowrap
    -0.06
    iance
    -0.06
    imu
    -0.06
    ültür
    -0.06
    ossip
    -0.06
    POSITIVE LOGITS
    aling
    0.09
    amma
    0.09
    isol
    0.08
    -Mar
    0.08
    ken
    0.08
    ables
    0.08
    ania
    0.08
    cone
    0.07
    aled
    0.07
    ika
    0.07
    Activations Density 0.005%

    No Known Activations