© 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. 72268
    Prev
    Next
    INDEX
    Explanations

    quotation marks and their associated content

    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
    icontrol
    -0.08
    ابط
    -0.08
    vÄĽd
    -0.08
    anca
    -0.08
    ternet
    -0.08
    ÑĥÑĩа
    -0.08
    çesi
    -0.07
    LOAT
    -0.07
    inode
    -0.07
    .enumer
    -0.07
    POSITIVE LOGITS
     There
    0.06
     We
    0.06
    linger
    0.05
     When
    0.05
     there
    0.05
     believe
    0.05
    ..↵
    0.05
     If
    0.05
    Ë
    0.05
     we
    0.05
    Activations Density 0.072%

    No Known Activations